Articles in Conference Proceedings

[Articles in Journals] [Articles in Conference Proceedings] [Chapters in Edited Volumes]
[Books] [Conference Proceedings] [Reports] [All Publications]

2024[ to top ]

Enhancing Maritime Behaviour Analysis through Novel Feature Engineering and Digital Shadow Modelling: A Case Study in Kiel Fjord. Al-Falouji, Ghassan; Gao, Shang; Haschke, Lukas; Nowotka, Dirk; Tomforde, Sven. In International Conference on Architecture of Computing Systems (ARCS), S. 97–111. Springer, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
With the continuous evolution of maritime technology, there is a growing need for analysing and modelling vessel behaviour in complex waterway systems. This paper presents an extension and utilisation of the Surface Vessel Nautical Behaviour Analysis (SV-NBA) framework for in-depth spatio-temporal analysis of maritime surface vessels’ behaviour in Kiel Fjord. Leveraging one year of collected Automatic Identification System (AIS) data, we extracted features from the recorded data. Three feature sets are generated and compared using expert-knowledge fea- tures, methods for feature selection, and Denoising Autoencoder latent space representation. Behaviour modelling and analysis utilises clustered data from the three feature sets, employing Gaussian Mixture Models (GMM). The trained GMM models serve as digital shadows, enabling storage-efficient representation of vessel behaviour and facilitates appli- cations such as online situational awareness and marine-traffic manage- ment. These digital shadows serve as observer-layer in a dynamic au- tonomous system of system, offering insights into maritime activities and enhancing navigation safety in busy waterways. This research contributes to the advancement of autonomous navigation systems and supports ef- ficient maritime traffic management strategies.
Introducing Generative Feedback to Chatbots in Digital Higher Education. Benner, Dennis. In International Conference on Wirtschaftsinformatik (WI). Würzburg, Germany, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The rapid evolution of the educational landscape, accentuated by the rise of Generative Artificial Intelligence (GAI), calls for a re-evaluation of digital education methodologies to harness new technologies and meet the changing needs of learners. Focusing on the potential of GAI, this study introduces a novel approach called generative feedback and explores its impact on the motivation, learning experience and performance of students in higher education. Therefore, this study presents a prototype that implements a GAI-driven chat using OpenAI’s GPT-4 turbo model to provide feedback to students. Using an overlap�ping study design that combines a longitudinal field study and a two-stage online experiment, this study investigates how generative feedback affects learners. Initial findings suggest that GAI-driven chatbots can provide meaningful feedback to students and enhance their learning experience, setting the stage for further investigation towards a better theoretical understanding of the design and practical application of GAI-driven chatbot feedback.
Engaging Minds – How Gamified Chatbots can Support and Motivate Learners in Digital Education. Benner, Dennis; Schöbel, Sofia; Janson, Andreas; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Blended and online learning is growing, and self-regulated learning is becoming more relevant. Most often, students struggle with organizing their own learning processes, lose focus or procrastinate. Keeping learners motivated and engaged can be a real challenge. Therefore, we present gamified chatbots as a potential solution. On the one hand, chatbots can provide a more engaging learning experience. On the other hand, gamification can provide motivational incentives to keep learners engaged and motivated. So far, not many studies have elaborated on how gamification can be effectively used to make a chatbot interaction more engaging or improve the learning experience. This study uses an experimental approach to distinguish how a combination of badges and a progress bar can support and motivate learners to stay engaged with their learning activities. We elaborate on the effects of gamified chatbots and support practitioners with guidance on how to design gamified chatbots in education.
The Rise of Generative AI in Low Code Development Platforms – An Analysis and Future Directions. Bruhin, Olivia; Dickhaut, Ernestine; Elshan, Edona; Li, Mahei Manhai. In Hawaii International Conference on System Sciences (HICSS). Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
This study investigates the relationship between Generative AI (GenAI) and Low Code Development Platforms (LCDPs), providing preliminary insights into Gen's transformative potential in this context. It is based on expert interviews and provides insight into the changing landscape of LCDPs influenced by GenAI. The findings highlight the promising benefits of GenAI in LCDPs, such as increased efficiency and decreased errors, while also emphasizing the importance of human oversight and collaboration. The findings also highlight the importance of interpersonal skills in IT, even in an increasingly automated environment. While the economic efficiency and broader implications of GenAI are still being investigated, the study lays the groundwork for future research in this rapidly evolving domain.
An Efficient Multi Quantile Regression Network with Ad Hoc Prevention of Quantile Crossing. Decke, Jens; Jenß, Arne; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), S. 51–66. Springer, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency. Integrating ad hoc sorting in training, the SCQRNN ensures non-intersecting quantiles, boosting model reliability and interpretability. We demonstrate that the SCQRNN not only prevents quantile crossing and reduces computational complexity but also achieves faster convergence than traditional models. This advancement meets the requirements of high-performance computing for sustainable, accurate computation. In organic computing, the SCQRNN enhances self-aware systems with predictive uncertainties, enriching applications across finance, meteorology, climate science, and engineering.
From Structured to Unstructured: A Comparative Analysis of Computer Vision and Graph Models in solving Mesh-based PDEs. Decke, Jens; Wünsch, Olaf; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), S. 82–96. Springer, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments. Focusing on structured, graded structured, and unstructured meshes, the study compares the performance and computational efficiency of three computer vision-based models against three graph-based models across three datasets. The research aims to identify the most suitable models for different mesh topographies, particularly highlighting the exploration of graded meshes, a less studied area. Results demonstrate that computer vision-based models, notably U-Net, outperform the graph models in prediction performance and efficiency in two (structured and graded) out of three mesh topographies. The study also reveals the unexpected effectiveness of computer vision-based models in handling unstructured meshes, suggesting a potential shift in methodological approaches for data-driven partial differential equation learning. The article underscores deep learning as a viable and potentially sustainable way to enhance traditional high-performance computing methods, advocating for informed model selection based on the topography of the mesh.
Conceptual Mapping of Controversies. Draude, Claude; Dürrschnabel, Dominik; Hirth, Johannes; Horn, Viktoria; Kropf, Jonathan; Lamla, Jörn; Stumme, Gerd; Uhlmann, Markus. In Conceptual Knowledge Structures, Bd. 14914, I. P. Cabrera, S. Ferré, S. Obiedkov (Hrsg.), S. 201–216. Springer Nature Switzerland, Cham, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
With our work, we contribute towards a qualitative analysis of the discourse on controversies in online news media. For this, we employ Formal Concept Analysis and the economics of conventions to derive conceptual controversy maps. In our experiments, we analyze two maps from different news journals with methods from ordinal data science. We show how these methods can be used to assess the diversity, complexity and potential bias of controversies. In addition to that, we discuss how the diagrams of concept lattices can be used to navigate between news articles.
Completing the Skills Puzzle: Developing a Skills Profile Data Model. Freise, Leonie Rebecca; Bretschneider, Ulrich. In 19. Internationale Tagung der Wirtschaftsinformatik (Wi24). Würzburg, Germany, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In today’s working world, driven by technological progress, there is a growing need to adapt and update skills to remain competitive. Employers need qualified employees, and employees want to develop their job-related skills, so skills profiles are becoming more prevalent. These profiles comprise skills that individuals bring to their jobs and develop over employment. When used effectively, they offer benefits in attracting, retaining, and developing talent, as well as in staffing and performance management. This paper proposes a data model for such profiles. Drawing upon a systematic literature review and interviews with employees, we derived the critical aspects of a skill profile data model. We further demonstrate the complexity and the need for a structured approach to include a bottom-up perspective. This research contributes to the theoretical understanding of skills profile data models by including the employee perspectives. It further provides insights for organizations to develop a skilled workforce.
Skills in Flux – Challenges in AI-based Skills Management and Skills Profiles. Freise, Leonie Rebecca; Bretschneider, Ulrich; Oeste-Reiss, Sarah. In 19. Internationale Tagung der Wirtschaftsinformatik (Wi24). Würzburg, Germany, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The changing world of work, driven by automation and digital tech-nologies, requires a workforce that continuously adapts its skills in order to be competitive and employable. This dynamic environment has fueled the demand for advanced skills management, with artificial intelligence (AI) playing a critical role in measuring and supporting individual skills development. This paper looks at AI-based competency profiles as a strategic tool for talent acquisition, reten-tion, and development and highlights their potential challenges. Using semi-structured interviews with experts from HR, education, and industry, we explore the multiple challenges of AI-based skills management from a theoretical, con-ceptual, and practical perspective. Our findings reveal complex problems at the individual, team, organizational, and systemic levels that form a basis for the de-velopment of effective AI-based skills management strategies. This research highlights the importance of using AI to foster an adaptable and skilled workforce that meets both current needs and future challenges.
Leading Teams in Today’s Dynamic Organizations: The Core Characteristics of Agile Leadership. Geffers, Kristin; Bretschneider, Ulrich; Eilers, Karen; Oeste-Reiß, Sarah. In Hawaii International Conference on System Sciences (HICSS). Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Agile leadership (AL) is essential for leading agile transformations. So far, a conceptualization of AL is still lacking. To investigate its core characteristics, we conduct an exploratory single case study. Our study examines a senior executive training program within a young European automotive software company, with the objective of establishing AL throughout the organization. Our study’s primary findings reveal that AL can be categorized into five perspectives: person-based, purpose-based, result-based, position-based, and process-based. Agile leaders are humble, adaptable, visionary, and engaged. AL focuses on aligning employees with a clear vision, fostering a learning organization, increasing transparency, and establishing decision-making in teams. It is practiced by executives, agile accountabilities, and team members. Agile leaders operate as experimenters, collaborators, facilitators, enablers, and resilient leaders. Our findings provide a foundational basis for organizations to implement AL, thereby enhancing their adaptability and overall success.
What is the Intrinsic Dimension of Your Binary Data? - and How to Compute it Quickly. Hanika, Tom; Hille, Tobias. In Conceptual Knowledge Structures - First International Joint Conference, CONCEPTS 2024, Cádiz, Spain, September 9-13, 2024, Proceedings, Bd. 14914 von Lecture Notes in Computer Science, I. P. Cabrera, S. Ferré, S. A. Obiedkov (Hrsg.), S. 97–112. Springer, 2024.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
A Repository for Formal Contexts. Hanika, Tom; Jäschke, Robert. In Proceedings of the 1st International Joint Conference on Conceptual Knowledge Structures. 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Data is always at the center of the theoretical development and investigation of the applicability of formal concept analysis. It is therefore not surprising that a large number of data sets are repeatedly used in scholarly articles and software tools, acting as de facto standard data sets. However, the distribution of the data sets poses a problem for the sustainable development of the research field. There is a lack of a central location that provides and describes FCA data sets and links them to already known analysis results. This article analyses the current state of the dissemination of FCA data sets, presents the requirements for a central FCA repository, and highlights the challenges for this.
Feldstudie zur Navigation autonomer mobiler Roboter an belebten öffentlichen Orten. Hegenberg, J.; Schmidt, L. In Arbeitswissenschaft in-the-loop - Mensch-Technologie-Integration und ihre Auswirkung auf Mensch, Arbeit und Arbeitsgestaltung: 70. Kongress der Gesellschaft für Arbeitswissenschaft (Stuttgart 2024), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (D.6.4). GfA-Press, Sankt Augustin, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Autonome mobile Roboter fahren zunehmend im öffentlichen Raum. Mögliche Konflikte zwischen der Fahrroute des Roboters und den Laufrouten der Passanten müssen so aufgelöst werden, dass die Passanten sich nicht gestört oder gefährdet fühlen und der Roboter dennoch effizient sein Ziel erreicht. Dazu wird eine Studie präsentiert, die nonverbale Kommunikation von Bewegungsabsichten mittels Blicken bzw. Kopfbewegungen im Feld erprobt. Bestehende Erkenntnisse aus künstlichen Szenarien und Laborstudien sowie zum menschlichen Verhalten werden im halböffentlichen Raum eines Einkaufszentrums einer Felderprobung unterzogen sowie vorläufige Ergebnisse präsentiert.
LiST: An All-Linear-Layer Spatial-Temporal Feature Extractor with Uncertainty Estimation for RUL Prediction. Huang, Zhixin; Gruhl, Christian; Sick, Bernhard. In IEEE Conference on Industrial Electronics and Applications(ICIEA). IEEE, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
In the context of Remaining Useful Life (RUL) prediction for industrial systems, the pursuit of prediction accuracy must be balanced against the hardware costs of model operation and the reliability of prediction results. To resolve these challenges, we introduce LiST, an all-linear-layer spatial-temporal feature extractor integrated with uncertainty estimation, specifically designed for processing sensor multivariate time series (MTS) data. Unlike traditional linear models that flatten MTS and thus neglect their spatial-temporal dependencies, LiST's linear layers act on both the sensor and time dimensions of MTS that can extract spatial and temporal features like GNN and RNN models. Through performance comparisons on four RUL prediction datasets, LiST uses only 66.1% of the parameters, achieves comparable accuracy to state-of-the-art GNN and RNN models, obtains the best results on two datasets with up to a 21.6% improvement in Score, and enhances training efficiency by 3.2 times. Additionally, LiST can predict RUL with uncertainty estimation and precisely disentangle epistemic and aleatoric uncertainties, thus enhancing the model's practicality and reliability in real-world industrial applications.
Time-Series Representation Learning via Heterogeneous Spatial-Temporal Contrasting for Remaining Useful Life Prediction. Huang, Zhixin; He, Yujiang; Nivarthi, Chandana Priya; Gruhl, Christian; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR). 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Classical contrastive learning paradigms rely on manual augmentations like cropping, masking, dropping, or adding noise randomly to create divergent sample views from original data. However, the choice of which method to manipulate samples is often subjective and may destroy the latent pattern of the sample. In response, this paper introduces a novel contrastive learning paradigm without choosing sample view augmentation methods, termed Heterogeneous Spatial-Temporal Representation Contrasting (HSTRC). Instead of sample view augmentation, we employ dual branches with a heterogeneous spatial-temporal flipped structure to extract two distinct hidden feature views from the same source data, which avoids disturbing the original time series. Leveraging a combination of cross-branch spatial-temporal contrastive and projected feature contrastive loss functions, HSTRC can effectively extract robust representations from unlabeled time series data. Remarkably, by only fine-tuning the fully connected layers on top of extracted representations by HSTRC, we achieve the best performance across several Remaining Useful Life prediction datasets, showing up to 19.2% improvements over the state-of-the-art supervised learning methods and classical contrastive learning paradigms. Besides, further intensive experiments demonstrate HSTRC's effectiveness in active learning, out-of-distribution testing, and transfer learning scenarios.
Spatial-Temporal Attention Graph Neural Network with Uncertainty Estimation for Remaining Useful Life Prediction. Huang, Zhixin; Nivarthi, Chandana Priya; Gruhl, Christian; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN), S. 1–9. IEEE, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
In the increasingly complex industrial system health management domain, accurate prediction of remaining useful life plays an essential role. This paper analyzes the methods to improve the predictive performance of remaining useful life from three aspects: optimizing model structures, augmenting uncertainty estimation in predictions, and transitioning normalization methods. Based on our analysis, we propose a novel model, the Uncertainty Spatial-Temporal Attention Graph Neural Network (USTAGNN), which consists of three primary components: sensor graph construction, a spatio-temporal feature extractor, and a probabilistic prediction module. The feature extractor leverages graph neural networks and temporal convolutional networks as a foundation to extract spatial and temporal features, further enhanced by attention mechanisms, spectral normalization, and residual connections to bolster its distance awareness. Following extensive experimental comparisons, we utilized the parameter-driven dynamic adjacency matrix for sensor graph construction and the deep kernel Gaussian process for precise uncertainty estimation. USTAGNN tries to resolve issues not thoroughly addressed in existing research, such as comparative analyses of sensor graph construction methods, accurate uncertainty estimation, and the model’s generalization under different preprocessing conditions. The proposed model demonstrated state-of-the-art performance on various subsets of the C-MAPSS dataset, achieving up to a 35.9% improvement in prediction score.
When to Use Smart Contracts Instead of Traditional Contracts – A Conceptual Analysis. Hupe, Anna. In 19th International Conference on Wirtschaftsinformatik (WI). Würzburg, Germany, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Smart contracts are code-based representations of business logic that encapsulate predefined rules that they verify and execute autonomously. As self-executing agreements, these contracts running on a blockchain facilitate interactions between untrusted parties, eliminating the need for intermediaries. They speed processes, increase transparency, and facilitate data exchange across national and organizational boundaries, providing a competitive advantage. However, there are significant costs associated with implementing smart contracts. In our study, we conduct a comparative analysis of these costs and compared them to traditional contracts. Using a combination of literature review and expert interviews, we dissect the cost structures of both approaches at an abstract level. We then construct a matrix to systematically compare traditional contracts with smart contracts. This framework allows us to model the conditions that favor the use of smart contracts over traditional ones, and to identify instances where each approach has a distinct advantage.
Governing the Crowd: Developing Reference Process Modules for the Governance of the Crowd on Online Labour Platforms. Hupe, Anna; Lange, Kirsten; Bretschneider, Ulrich; Refflinghaus, Robert. In International Working Seminar on Production Economics (IWSPE). Innsbruck, Austria, 2024.
- [ URL ]
- [ BibSonomy-Post ]
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification. Huseljic, Denis; Hahn, Paul; Herde, Marek; Rauch, Lukas; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), S. 280–296. 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait in their evaluation. This paper introduces two methods to enhance \\textsc{Bait's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox.
FinDEx: A Synthetic Data Sharing Platform for Financial Fraud Detection. Karst, Fabian; Li, Mahei Manhai; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). University of Hawaiʻi at Mānoa, Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The rising number of financial frauds inflicted in the last year more than 800 billion USD in damages on the global economy. Although financial institutions possess advanced AI systems for fraud detection, the time required to accumulate a sufficient volume of fraudulent data for training models creates a costly vulnerability. Combined with the inability to share fraud detection training data among institutions due to data and privacy regulations, this poses a major challenge. To address this issue, we propose the concept of a synthetic data-sharing ecosystem platform (FinDEx). This platform ensures data anonymity by generating synthesized training data based on each institution's fraud detection datasets. Various synthetic data generation techniques are employed to rapidly construct a shared dataset for all ecosystem members. Using design science research, this paper leverages insights from financial fraud detection literature, data sharing practices, and modular systems theory to derive design knowledge for the platform architecture. Furthermore, the feasibility of using different data generation algorithms such as generative adversarial networks, variational auto encoder and Gaussian mixture model was evaluated and different methods for the integration of synthetic data into the training procedure were tested. Thus, contributing to the theory at the intersection between fraud detection and data sharing and providing practitioners with guidelines on how to design such systems.
Erprobung eines innovativen Unternehmensberatungskonzepts für neue Technologien am Beispiel von 3D-Scannern und -Druckern. Landau, E.; Schmidt, L. In Arbeitswissenschaft in-the-loop - Mensch-Technologie-Integration und ihre Auswirkung auf Mensch, Arbeit und Arbeitsgestaltung: 70. Kongress der Gesellschaft für Arbeitswissenschaft (Stuttgart 2024), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (H.3.5). GfA-Press, Sankt Augustin, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Im Beitrag wird der Entwicklungsstand eines Unternehmensberatungskonzepts für kleine und mittlere Unternehmen (KMU) aus Produktion und Handwerk am Beispiel von 3D-Scannern und -Druckern vorgestellt. Ziel ist es, den Beschäftigten ein selbstständiges Austesten neuer Technologien anhand praxisnaher Anwendungsfälle zu ermöglichen. Dabei wurde in einem Mixed-Method-Design untersucht, ob die pädagogischen und didaktischen Werthaltungen bzw. Überzeugungen, u. a. Anchored Instruction und Cognitive Apprenticeship, umgesetzt und die Lernziele erreicht wurden. Es werden erste Ergebnisse der Evaluation des Konzepts aus einer Pilotstudie (N = 5) vorgestellt, diskutiert und Maßnahmen für die iterative Überarbeitung abgeleitet.
Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis. Lehna, Malte; Hassouna, Mohamed; Degtyar, Dmitry; Tomforde, Sven; Scholz, Christoph. In Machine Learning for Sustainable Power Systems (ML4SPS), ECML. Springer, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.
More Than Just Efficiency: Impact of Generative AI on Developer Productivity. Li, Mahei; Dickhaut, Ernestine; Bruhin, Olivia; Wache, Hendrik; Weritz, Pauline. In Americas Conference on Information Systems (AMCIS). Utah, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The collaboration between genAI and humans in the field of information systems holds transformative potential echoing the co-creation ethos in digital ecosystems. GenAI's automated code generation capabilities present an opportunity for seamless cooperation with human developers. As genAI evolves, it can contribute to the generation of code with minimal human input, enabling developers to focus on higher-level conceptualization and problem-solving. The individual work changes by GenAI also have wider-reaching effects, which requires a holistic understanding of its impact. Our interview study with 15 software developers presents a shift towards a more balanced viewpoint on measuring the effects of genAI in software development environments, specifically the importance of human-centric indicators (e.g. satisfaction and wellbeing) in addition to traditional efficiency and effectiveness indicators. This insight underscores the balancing act between enhancing productivity and potentially undermining it, reflecting the interplay of co-creation and co-destruction in service ecosystems and calling for a more holistic socio- technical perspective.
Einsatz von Virtual Reality zum Erlernen eines Montageprozesses. Mack, D.; Funk, J.; Schmidt, L. In Arbeitswissenschaft in-the-loop - Mensch-Technologie-Integration und ihre Auswirkung auf Mensch, Arbeit und Arbeitsgestaltung: 70. Kongress der Gesellschaft für Arbeitswissenschaft (Stuttgart 2024), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (H.4.2). GfA-Press, Sankt Augustin, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Für die Montage von komplexen Baugruppen soll ein Schulungsangebot entwickelt werden, welches auch ohne Sprachbarriere ein niedrigschwelliges Anlernen neuer Arbeiter ermöglicht. In der hier vorgestellten Studie wurden zwei Arten von Montagetrainings für die Montage einer realen Baugruppe eines mittelständischen Unternehmens verglichen. Eine Gruppe wurde in einer VR-Trainingssimulation geschult. Die Kontrollgruppe wurde mit einem Video aus der Egoperspektive der VR-Anwendung trainiert. Dabei wurden die Gebrauchstauglichkeit (SUS) und die Beanspruchung (NASA-TLX) bei der Verwendung der Anwendungen getestet. Anschließend wurde die komplexe Baugruppe an einem Montagearbeitsplatz montiert, wobei die benötigte Zeit und die gemachten Fehler protokolliert wurden.
Unterstützung einer komplexen Montageaufgabe durch eine Augmented-Reality-Anleitung mit Durchsichtdatenbrille. Mack, D.; Schmidt, L. In DELFI 2024: 22. Fachtagung Bildungstechnologien (Fulda 2024), von Lecture Notes in Informatics (LNI) - Proceedings, S. Schulz, N. Kiesler (Hrsg.), S. 49–62 *** Best Paper Candidate ***. Gesellschaft für Informatik, Bonn, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die hier vorgestellte Studie betrachtet die Montage eines Notgriffs zur Türentriegelung von Schienenfahrzeugen an einem originalgetreuen Arbeitsplatz mit unterschiedlichen Anleitungen. Dazu wurde eine AR-Anleitung mit einer Durchsichtdatenbrille neu entwickelt und mit einer Smartphone- basierten AR-Anleitung sowie einer Papieranleitung verglichen. Die Papieranleitung stellt den Status Quo in der Montage dar. Die Umsetzung mit einer Durchsichtdatenbrille ist zwar technisch aufwändiger, hat aber gegenüber dem bereits untersuchten Smartphone den Vorteil, dass die Hände für die Montage frei sind. Die untersuchten Hypothesen sind, dass die Anleitungsart einen Einfluss auf die Montagezeit, die Anzahl der Fehler, die Gebrauchstauglichkeit und die Beanspruchung der montierenden Personen hat. Jede Anleitungsart wurde mit acht Probanden und fünf Montagedurchgängen in einem Between- Subject-Design untersucht. Zwischen Durchsichtdatenbrille und Smartphone zeigte sich bei der Gesamtmontagedauer kein signifikanter Unterschied. Eine vergleichbare Fehleranzahl bei geringerer Beanspruchung macht die Durchsichtdatenbrille dennoch interessant für die Wissensvermittlung.
Adaptive Shapley: Using Explainable AI with Large Datasets to Quantify the Impact of Arbitrary Error Sources. Magnussen, Birk Martin; Jessulat, Maik; Stern, Claudius; Sick, Bernhard. In International Conference on Big Data Analytics (ICBDA), S. 305–310. IEEE, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Almost all sensors suffer from some level of uncertainty introduced from production inaccuracies. When the sensor data is processed by machine learning, quantifying the impact of such production inaccuracies on the output of the machine learning model becomes difficult. Certain neural network architectures, such as continuous feature networks, allow individual features and data to be omitted while still being able to correctly predict the result without the need for retraining. Such features can, for example, be individual channels of a sensor. This article proposes a method to use the capability to omit arbitrary features or sensor channels to calculate Shapley values for each sensor channel. These Shapley values represent the contribution of each individual channel to the measurement. They are defined using an arbitrary function called the ``value function''. If the value function is defined as the error of the current measurement, the Shapley values will represent the contribution of each sensor channel to the error of the measurement result. By calculating Shapley values like this for a large unlabelled dataset of measurements, it is possible to understand how much measurement error was introduced by which channel of which sensor in each measurement. Averaging the Shapley values for each sensor in the dataset will then result in a metric for each channel of that sensor, which represents a contribution to measurement errors. By comparing these values to any arbitrary quality metrics for the sensor channels obtained in a calibration process or similar step, it is possible to correlate and quantify which value in the quality metric will cause how much of a measurement error, or whether the quality metric is even relevant for the measurement accuracy. This article will show the efficacy and use case of the method on an example of the production and quality control of optical sensors based on multiple spatially resolved reflection spectroscopy.
Optical Detection of the Body Mass Index and Related Parameters Using Multiple Spatially Resolved Reflection Spectroscopy. Magnussen, Birk Martin; Möckel, Frank; Jessulat, Maik; Stern, Claudius; Sick, Bernhard. In International Conference on Bioinformatics and Computational Biology (ICBCB). IEEE, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
Obesity is a common problem for many people. In order to assist people combating obesity, providing methods to quickly, easily, and inexpensively assess their body composition is important. This article investigates how noninvasive, optical sensors based on multiple spatially resolved reflection spectroscopy can be used to measure the body mass index and body composition parameters. Using machine learning to train continuous feature networks, it is possible to predict the body mass index of a subject, with a correlation of $$R=0.61$$ with $$p<0.0001$$. Similarly, the predicted body mass index shows correlations to both the subject's visceral fat ($$R=0.44,p=0.0023$$) and skeletal muscle mass index ($$R=0.52,p=0.0003$$), indicating that the trained neural network is capable of identifying both types of tissue. Strategies to independently detect either type of tissue are discussed.
Multi-Task Representation Learning with Temporal Attention for Zero-Shot Time Series Anomaly Detection. Nivarthi, Chandana Priya; Huang, Zhixin; Gruhl, Christian; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN), S. 1–10. IEEE, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. However, accurately labelling anomaly datasets is challenging due to their rarity and manual annotation subjectivity. The conventional approach of training separate models for each dataset entity further complicates model development. This paper presents a novel Multi-task Learning framework combining LSTM Autoencoder with temporal attention mechanism (MTL-LATAM) for effective time series anomaly detection. Multitask learning models improve adaptability and generalizability, leading to reduced runtime and compute power while supporting zero-shot evaluation. These models offer flexibility in detecting emerging anomalies. Additionally, we introduce a dynamic thresholding mechanism to incorporate temporal context for anomaly detection and provide visualizations of attention weights to enhance interpretability. The study compares MTL- LATAM, with other multi-task models, evaluates multi-task versus single-task models and assesses the performance of the proposed frame- work in zero-shot learning scenarios. The findings indicate MTL- LATAM’s effectiveness across real-world and open-source datasets, achieving 95% and 97% task synergy. The results underscore the superior performance of multi-task models in zero-shot tasks compared to individual models trained exclusively on their respective datasets.
Generative AI in Customer Support Services: A Framework for Augmenting the Routines of Frontline Service Employees. Reinhard, Philipp; Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Customer support service employees are facing an increased workload, while artificial intelligence (AI) appears to possess the potential to change the way we work. With the advent of modern types of generative AI, new opportunities to augment frontline service employees have emerged. However, little is known about how to integrate generative AI in customer support service organizations and purposefully change service employee work routines. Following multi-method qualitative research, we performed a literature review, conducted workshops, and interviewed IT support agents, managers, and AI experts. Thereby, we examine AI augmentation for frontline service employees in the context of IT support to carve out where and how GenAI can be leveraged to develop more efficient and higher-quality customer support. Our resulting framework reveals that especially adapting solutions and retaining knowledge is subject to a high degree of AI augmentation.
LET EMPLOYEES TRAIN THEIR OWN CHATBOTS: DESIGN OF GENERATIVE AI-ENABLED DELEGATION SYSTEMS. Reinhard, Philipp; Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In European Conference on Information Systems (ECIS). Paphos, Cyprus, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
While chatbots can be implemented with very little effort, scaling and maintaining chatbots remains a challenge. This is crucial in knowledge-intensive customer service like IT support, where domain knowledge must stay current with the evolving IT landscape. Following design science research, we derive design principles for a generative AI (GPT4) enabled textual training data creation and curation system (T²C²) as part of a new class of systems – bot delegation systems. For the design of T²C², chatbot and domain expert viewpoints are integrated. We evaluate two instances of T²C², each with distinct degrees of human-ai delegation where employees act both as creators and curators of training data. The paper’s theoretical contribution is two-fold: (1) we present a novel kernel theory that represents the material characteristics of bot delegation systems by contextualizing the IS delegation framework to the self-determination theory; (2) the design and evaluation of T²C² as the built-and-evaluated artifact.
Augmenting Frontline Service Employee Onboarding via Hybrid Intelligence: Examining the Effects of Different Degrees of Human-GenAI Interaction. Reinhard, Philipp; Neis, Nicolas; Kolb, Lisa; Wischer, Dennis; Li, Mahei Manhai; Winkelmann, Axel; Teuteberg, Frank; Lechner, Ulrike; Leimeister, Jan Marco. In International Conference on Design Science Research in Information Systems and Technology (DESRIST 2024), M. Y. Mandviwalla, M. Söllner, T. Tuunanen (Hrsg.). Trollhättan, Sweden, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
High turnover rates within help desks, caused by excessive workloads, make the efficient onboarding of novices a persistent and recurring challenge. Generative artificial intelligence (GenAI) possesses the potential to augment novice frontline service employees (FSE) during their onboarding phase. However, there is a lack of knowledge on how to design the interaction of FSE and GenAI. Thus, following design science research (DSR), we propose a conversational (co-)agent that leverages the capabilities of large language models and the concept of hybrid intelligence to augment novice FSE. To examine the interaction between novices and GenAI given various task difficulties, we derive and instantiate two hybrid intelligence meta-designs - a supporter that provides recommendations and a collaborator that allows for prompting the coagent. The results from an online experiment with 75 laypeople show that novices interact with GenAI more frequently and show a higher engagement, especially in difficult tasks. Overall, we uncover a paradox: Despite an increased interaction and a greater time investment, FSEs experience a lower perceived workload with a GenAI-based collaborator. From that, we derive implications for designing employee-facing co-agents in customer services.
Balancing Bytes with Brains: Exploring the Role of Learners’ Control in Personalized Learning Tasks. Ritz, Eva. In European Conference on Information Systems (ECIS). Paphos, Cyprus, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The increasing prevalence of artificial intelligence (AI)-based learning systems unleashes new potentials in designing personalized learning experiences that enhance learning outcomes. However, prior research indicates that such systems can negatively impact engagement due to issues in human information processing. This study examines whether giving learners control over task difficulty selection in personalized learning systems can mitigate these effects. A laboratory within-subjects experiment involving 80 participants explored how control over personalized vocabulary learning affects learning performance and autonomy satisfaction. As such a control feature may lead to deeper information processing, I investigate the mediating effect of cognitive workload on the main effect. The study aims to contribute to human-AI interaction literature by shedding light on the importance of control in personalized system design and investigating its effects on cognitive workload, overall task performance, and autonomy satisfaction.
What to Learn Next? Designing Personalized Learning Paths for Re-&Upskilling in Organizations. Ritz, Eva; Freise, Leonie; Elshan, Edona; Rietsche, Roman; Bretschneider, Ulrich. In Hawaii International Conference on System Sciences (HICSS). Waikiki, Hawaii, USA, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The fast-paced acceleration of digitalization requires extensive re-&upskilling, impacting a significant proportion of jobs worldwide. Technology-mediated learning platforms have become instrumental in addressing these efforts, as they can analyze platform data to provide personalized learning journeys. Such personalization is expected to increase employees’ empowerment, job satisfaction, and learning outcomes. However, the challenge lies in efficiently deploying these opportunities using novel technologies, prompting questions about the design and analysis of generating personalized learning paths in organizational learning. We, therefore, analyze and classify recent research on personalized learning paths into four major concepts (learning context, data, interface, and adaptation) with ten dimensions and 34 characteristics. Six expert interviews validate the taxonomy’s use and outline three exemplary use cases, undermining its feasibility. Information Systems researchers can use our taxonomy to develop theoretical models to study the effectiveness of personalized learning paths in intra-organizational re-&upskilling.
The Promise of Evaluative Algorithmic Advice: A Field Experiment on Writing Improvement. Schmitt, Anuschka; Wambsganss, Thiemo; Janson, Andreas; Gajos, Krzysztof. In Academy of Management (AOM) Meeting. Chicago, IL, USA, 2024.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
The design and impact of algorithmic advice has become more important than ever with generative artificial intelligence’s (AI) diffusion in organizational and private realms. Unfortunately, challenges associated with the computational nature of AI-based systems and human sensemaking can hinder augmentation of human work. Prevalent forms of algorithmic advice commonly provide a user with ‘one best’ solution that can induce the user to fixate on the advice and neglect own critical reasoning. To overcome such interaction challenges, we explore the potential of evaluative algorithmic advice that provides users with more open-ended and engaging feedback. As part of two controlled experiments, we find that humans prefer evaluative over contrastive advice for writing feedback. We then conducted a field experiment in the context of an educational business pitch writing task with two conditions: (i) contrastive algorithmic advice improving users’ writing without any further feedback; and (ii) evaluative algorithmic advice providing feedback in form of open-ended questions and pro and contra arguments. Users’ writing could be improved regardless of the type of algorithmic advice, yet we show that users exposed to evaluative advice engaged significantly more with the task and the advice. Our study explores how algorithmic advice may serve as a critical stimulator rather than attenuating human agency in AI augmentation.
Worked Examples to Facilitate the Development of Prompt Engineering Skills. Tolzin, Antonia; Knoth, Nils; Janson, Andreas. In Thirty-Second European Conference on Information Systems (ECIS 2024). Paphos, Cyprus, 2024.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
This paper explores the evolving field of prompt engineering in Artificial Intelligence (AI), with a focus on Large Language Models (LLMs). As LLMs exhibit remarkable potential in various educational domains, their effective use requires adept prompt engineering skills. We introduce a skill-based approach to prompt engineering and explicitly investigate the impact of using worked examples to facilitate prompt engineering skills among students interacting with LLMs. We propose hypotheses linking prompt engineering, worked examples, and perceived anthropomorphism to the quality of LLM output. Our initial findings support the critical relationship between proficient prompt engineering and the resulting output quality of LLMs. Subsequent phases will further explore the role of worked examples in prompt engineering, aiming to provide practical recommendations for educational improvement and industry application. Additionally, this research aims to shed light on the responsible utilization of LLMs in education and contribute insights to educational practice, research, and organizational development.
Empirische Evaluation von personalisierten Fahrgastinformationen auf einem Smart Public Display. Wehr, F.; Beckers, L.; Schmidt, L. In Arbeitswissenschaft in-the-loop - Mensch-Technologie-Integration und ihre Auswirkung auf Mensch, Arbeit und Arbeitsgestaltung: 70. Kongress der Gesellschaft für Arbeitswissenschaft (Stuttgart 2024), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (D.2.1). GfA-Press, Sankt Augustin, 2024.
- [ Abstract ]
- [ BibSonomy-Post ]
In der hier vorgestellten Laborstudie wurde ein Smart Public Display mit personalisierten Fahrgastinformationen des öffentlichen Personennahverkehrs mit dem Stand der Technik, einem Public Display mit allgemeinen Fahrgastinformationen nahegelegener Haltestellen, verglichen. Unter Einbezug des Abstands einer umstehenden Person wurde die Technologieakzeptanz mit dem TUI-, die Gebrauchstauglichkeit mit dem SUS- und die Nutzererfahrung mit dem UEQ-Fragebogen erhoben. Die Ergebnisse zur Technologieakzeptanz zeigen keine signifikanten Unterschiede. Hinsichtlich der Gebrauchstauglichkeit und Nutzererfahrung deuten die Unterschiede darauf hin, dass Weiterentwicklungspotential, aber auch ein Mehrwert des Smart Public Displays mit personalisierten Fahrgastinforma-tionen gegenüber dem Public Display bestehen.

2023[ to top ]

Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering. Aßenmacher, Matthias; Rauch, Lukas; Goschenhofer, Jann; Stephan, Andreas; Bischl, Bernd; Roth, Benjamin; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, S. 65–73. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.
Stay with me - Conversational Churn Prevention in Digital Subscription Service. Benner, Dennis; Schöbel, Sofia. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Lots of organizations use subscription business models. However, with increasing competition and technological progress switching costs for customers are decreasing. This development can translate to serious issues for subscription-based businesses, requiring action. Traditionally, businesses used mailings or calls, which are costly, time-consuming and often not effective. In this research-in-progress paper, we explore conversational churn prevention as a potential remedy. We present a conversational agent with persuasive design features (e.g., nudges) and first results from a pre-study. We conduct an in-between subject experiment and interviews for our mixed-methods evaluation of our pre-study. Our work contributes to theory, by presenting more insights into the interaction quality of conversational agents in the context of churn prevention of digital services and the role of persuasive design. We support practitioners, by guiding them towards more effective use of conversational agents to improve their services and to predict churn.
Measuring students’ argumentation skills: validation of a test instrument. Berkle, Yvonne; Janson, Andreas; Wambsganß, Thiemo; Löfflad, Denise; Leimeister, Jan Marco; Leuchter, Miriam. In EARLI Conference (EARLI). Thessaloniki, Greece, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
The importance of argumentation skills for academic disciplines is well evident. Two core aspects of argumentation skills are a) the recognition of argumentation fallacies and b) the recognition of the structure of arguments. These two argumentation skills might be related to domain-specific knowledge. In our study, we aim to evaluate an instrument to assess the recognition of argumentation fallacies and the structure of arguments in the context of different domains. Thus, we implemented a self-developed instrument to measure both argumentation skills in different student groups (business economic students and pre-service teachers) in different domains: a) the study-domain of their own courses, b) the study-domain of the respective other courses and c) a neutral domain (sustainability). We assumed these three domains to represent different dimensions within the ability to recognize argumentation fallacies and within the ability to recognize argument structures. This assumption could not be confirmed, what leads to the assumption that our instrument captures cross-domain argumentation skills. However, our research implies a difference in the recognition of formal compared to informal argumentation fallacies. Furthermore, the results indicate that the instrument measures argumentative skills in both groups of students equally well.
What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving. Breitenstein, Jasmin; Heidecker, Florian; Lyssenko, Maria; Bogdoll, Daniel; Bieshaar, Maarten; Zöllner, J. Marius; Sick, Bernhard; Fingscheidt, Tim. In Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV, S. 3991–4000. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.
Stores are Liable for Their Robots!? An Empirical Study on Liability in HRI with an Anthropomorphic Frontline Service Robot. Busch, Philip; Kirchhoff, Jérôme; Heinisch, Judith S.; David, Klaus; von Stryk, Oskar; Wendt, Janine. In 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). 2023.
- [ BibSonomy-Post ]
DADO – Low-Cost Query Strategies for Deep Active Design Optimization. Decke, Jens; Gruhl, Christian; Rauch, Lukas; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), S. 1611–1618. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.
Sharing Design Knowledge Through Codification in Interdisciplinary DSR Collaborations. Dickhaut, Ernestine; Janson, Andreas; Hevner, Alan; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The goals of design science research (DSR) projects are to generate novel and useful artifacts and to produce rigorous and generalizable design knowledge. Often, DSR projects are conducted in collaborative, interdisciplinary project teams. Different disciplinary approaches to codifying design knowledge result in challenging project interactions. To study this situation, we analyze design knowledge codification in interdisciplinary teams over time. We gain insights from a survey of recent DSR papers that have been published in the AIS Senior Scholars’ Basket. We then present a detailed case study of a longitudinal project that brought to light issues of sharing design knowledge across disciplinary borders. Drawing from the survey and case study, we provide actionable guidance on how to effectively codify and share design knowledge to support researchers and practitioners to build useful artifacts and to make interdisciplinary design knowledge contributions reusable and applicable.
How Videoconferencing and its Affordances Transformed Teaching in Schools During COVID-19 Pandemic. Dickhaut, Ernestine; Li, Mahei Manhai; Janson, Andreas. In Hawaii international conference on system sciences (HICSS). Maui, Hawaii, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The COVID-19 pandemic has brought about major changes in digitization in many areas of life and professions. New areas were digitized almost overnight, the school system in Germany was no exception leading to a demand for videoconferencing tools and communication platforms. These technologies have many different functionalities that need to be discovered, explored, and exploited by the user. Given the disruptive events that the COVID pandemic brought to us, this paper aims to shed light on how the dynamics of discovery, exploration, and exploitation unfolds. We use a functional affordance theory perspective to analyze and understand how user learn to use new technologies. To do this, we conducted an exploratory case-study-based research design including interviews with teachers from various schools to analyze how they appropriate new technologies to develop an explanatory theoretical model.
Working with Diversity in Informatics. Draude, Claude. In Hochschuldidaktik Informatik HDI 2021, von Commentarii informaticae didacticae, S. 13–33. Universitätsverlag Potsdam, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Diversity is a term that is broadly used and challenging for informatics research, development and education. Diversity concerns may relate to unequal participation, knowledge and methodology, curricula, institutional planning etc. For a lot of these areas, measures, guidelines and best practices on diversity awareness exist. A systemic, sustainable impact of diversity measures on informatics is still largely missing. In this paper I explore what working with diversity and gender concepts in informatics entails, what the main challenges are and provide thoughts for improvement. The paper includes definitions of diversity and intersectionality, reflections on the disciplinary basis of informatics and practical implications of integrating diversity in informatics research and development. In the final part, two concepts from the social sciences and the humanities, the notion of “third space”/hybridity and the notion of “feminist ethics of care”, serve as a lens to foster more sustainable ways of working with diversity in informatics.
Maximal Ordinal Two-Factorizations. Dürrschnabel, Dominik; Stumme, Gerd. In Graph-Based Representation and Reasoning, M. Ojeda-Aciego, K. Sauerwald, R. Jäschke (Hrsg.), S. 41–55. Springer Nature Switzerland, Cham, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
Given a formal context, an ordinal factor is a subset of its incidence relation that forms a chain in the concept lattice, i.e., a part of the dataset that corresponds to a linear order. To visualize the data in a formal context, Ganter and Glodeanu proposed a biplot based on two ordinal factors. For the biplot to be useful, it is important that these factors comprise as much data points as possible, i.e., that they cover a large part of the incidence relation. In this work, we investigate such ordinal two-factorizations. First, we investigate for formal contexts that omit ordinal two-factorizations the disjointness of the two factors. Then, we show that deciding on the existence of two-factorizations of a given size is an {\$$}{\$$}{\backslash}textsf{\{}NP{\}}{\$$}{\$$}NP-complete problem which makes computing maximal factorizations computationally expensive. Finally, we provide the algorithm Ord2Factor that allows us to compute large ordinal two-factorizations.
An Investigation of Why Low Code Platforms Provide Answers and New Challenges. Elshan, Edona; Dickhaut, Ernestine; Ebel, Philipp. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Although the idea of low code development is not new, the market for these oftentimes platform-based development approaches is exponentially growing. Especially factors such as increasing affinity for technology development across all user groups, consumerization of development, and advancing digitalization are opening a new target group for the low code movement. The broad application possibilities of low code, as well as the benefits, are therefore getting more important for businesses. Especially for small and medium-sized enterprises (SMEs), low code constitutes a promising avenue to survive and succeed in the rapidly changing world. However, a clear understanding regarding the application of this paradigm of software development in SMEs is still missing. To provide a coherent understanding of the phenomenon low code in SMEs, we review extant literature and conduct interviews, identifying potential application domains and conceptualizing the benefits and challenges of low code from a holistic perspective.
Faster, Cheaper, Better? Analyzing how Lowcode Developoment Platforms drive Bottom-Up Innovation. Elshan, Edona; Germann, Dominic; Dickhaut, Ernestine; Li, Mahei Manhai. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recent years have seen a growing adoption of Low Code Development Platforms (LCDPs) in organizations. The increasing affinity for technology development across all user groups, consumerization of development, and advancing digitalization are opening up a new target group for the low code movement. This change in software development allows bottom-up user innovators within a company to leverage their domain knowledge and quickly deploy much-needed digital services. However, a clear understanding of this paradigm of software development in organizations and the influence on end-user acceptance is still missing. In this paper, we present the results of an interview study conducted with 18 LCDP experts and discuss the implications of our findings, highlighting the role of LCDPs and context in bottom-up innovation as well as user-centricity. Our research contributes to the literature on LCDPs and offers valuable insights for organizations looking to leverage their workforce's innovative potential.
Integrating Multiple Logics by Design? Developing an Approach for Designing Digital Business Models. Engert, Simon; Horn, Viktoria; Draude, Claude; Hess, Thomas. In ACIS 2023 Proceedings. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Current approaches to the design and development of digital business models (DBMs) overlook the multiple, and sometimes conflicting, logics of actors with which the focal firm seeks to co-create value. The lack of integrating stakeholders’ logics into DBMs has potentially detrimental and unintended ethical and social consequences. By collaboratively conducting an action research project with a digital publisher and drawing on participatory and value-sensitive design principles, we develop a novel approach for designing DBMs that integrates actors’ multiple logics by design. We contribute to literature by introducing a new approach highlighting DBMs’ inherent social aspects and furthering our understanding of multiple logics’ role in DBMs. Practitioners gain a concrete DBM design method preempting conflict.
Self-awareness in Cyber-Physical Systems: Recent Developments and Open Challenges. Esterle, Lukas; Dutt, Nikil; Gruhl, Christian; Lewis, Peter R.; Marcenaro, Lucio; Regazzoni, Carlo; Jantsch, Axel. In Design, Automation & Test in Europe Conference & Exhibition (DATE), S. 1–6. IEEE, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in Cyber-Physical Systems where computing systems have to control and interact with elements in the real world. This paper reports on recent advances made in computational self-awareness for cyber-physical systems.
Automized Assessment for Professional Skills – A Systematic Literature Review and Future Research Avenues. Freise, Leonie Rebecca; Bretschneider, Ulrich. In Internationale Tagung Wirtschaftsinformatik (WI). Paderborn, Germany, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Globalization, technological progress, and demographic trends increasingly influence our labor markets. With changing labor markets and increasing digitalization, new competencies of workers are needed to meet demands. However, as a first step to developing these new skills, knowledge about the existing skills and their status quo is necessary. Here, automated skill assessment offers a crucial added value, as it can create a reliable and objective database. Based on a systematic investigation, our analysis shows, in four different areas, how skills and competencies in the automated assessment are (1) defined, (2) included as an element of analysis, (3) methodically recorded and processed, (4) which data source is used. In doing so, we offer insights into existing approaches to automated assessment of professional skills. We contribute to a better under-standing of the design of automated skill assessment methods and provide perspectives on future research directions.
Transferring Digital Twin Technology on Employee Skills: A Framework to Support Human Resources. Freise, Leonie Rebecca; Hupe, Anna. In Academy of Management Annual Meeting (AOM). Boston, Massachusetts, USA, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
Skill assessment has become increasingly important in recent years. The shortage of skilled workers has demonstrated the need to identify suitable candidates for jobs and to develop existing employees. However, human resources processes rely on resumes, references, or job certifications to assess their employees’ skills. A few years ago, the concept of a digital twin was introduced, which is a digital replica of a physical entity. While using blockchain, the digital twin technology offers tremendous potential for transfer to other contexts. In the context of these considerations, we present a framework that allows the technology of the digital twin to be combined with that of skill assessment to create an enhanced skill profile. With a job market signaling perspective, we integrate knowledge about skills, clarify the opportunities of assessment, and develop a framework for a digital skill twin. In doing so, we argue that the multi-source and multi-method approach of such a digital skill twin leads to increased validity, reliability, and standardization. We thereby contribute to theory and practice by developing a new framework that offers employees to know their strengths and development potential and organizations to assess their employees’ skills.
Scaling Dimension. Ganter, Bernhard; Hanika, Tom; Hirth, Johannes. In Formal Concept Analysis - 17th International Conference, ICFCA 2023, Kassel, Germany, July 17-21, 2023, Proceedings, Bd. 13934 von Lecture Notes in Computer Science, D. Dürrschnabel, D. López-Rodríguez (Hrsg.), S. 64–77. Springer, 2023.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Meetings at Digital Workplaces – An Experimental Approach to Analyze Group Attachment and Organizational Commitment in Digital Worlds. Gleich, Tristan; Schöbel, Sofia; Janson, Andreas. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
After facing the COVID-19 pandemic, organizations request their employees to work from home permanently. For an organization, this provides positive benefits such as reducing costs for rent. From an employee perspective, working from home can cause a feeling of isolation towards co-workers and lower attachment to an organization. One way to counteract this problem is to transfer the office to the digital world, especially spurred by the metaverse discussion to represent processes of our real world in digital environments that allow us to do everything in the same way digitally as we are doing in the real world. In this paper, we present a theoretical model for conducting a 2x2 between-subject experiment to analyze how digital real-world meeting experiences influence team attachment and organizational commitment. We contribute to theories such as the need of belonging and transfer them to digital environments and provide practical implications for designing digital offices.
WHERETO FOR AUTOMATED COACHING CONVERSATION: STRUCTURED INTERVENTION OR ADAPTIVE GENERATION?. Göldi, Andreas; Rietsche, Roman. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
In an age of lifelong learning, it is important that adult learners can effectively use their motivation and resources to reach their learning goals. In conversation, coaches can intervene to promote learning goal attainment by using behavioural change techniques (BCTs). In a coaching chatbot, such techniques can be ordered in an established, structured way to good effect. With recent technological advances, chatbot responses can be generated adaptively; this means that BCTs can be applied in an adaptive but less structured way. It is yet unclear whether this latter form of configuring coaching interventions is viable, how they compare to more established structured interventions, and whether both methods can be combined. For the purpose of answering this, we propose a 2x2 experimental design with the two intervention types as factors and goal attainment as the dependent variable. Results will indicate avenues for automating skilled conversation including choice of technology.
Self-Integration and Agent Compatibility. Gruhl, Christian; Sick, Bernhard. In Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), S. 71–73. IEEE, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This position paper addresses the issue of agent compatibility in the context of self-aware microsystems (SAMs), which are SISSY systems with self-awareness capabilities. SAMs are designed to adapt their behaviour and collaborate with other agents in multi-agent settings. Achieving compatibility and effective collaboration between agents pose significant challenges, such as detecting incompatibility and discerning it from malicious behaviour. We present our concept of agent compatibility, highlight future challenges, and propose directions for future research in this area. By focusing on agent compatibility, we aim to advance the understanding of SAMs and promote successful collaboration among agents.
Context Information for Corner Case Detection in Highly Automated Driving. Heidecker, Florian; Susetzky, Tobias; Fuchs, Erich; Sick, Bernhard. In IEEE International Conference on Intelligent Transportation Systems (ITSC), S. 1522–1529. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.
Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning. Herde, Marek; Huseljic, Denis; Sick, Bernhad; Bretschneider, Ulrich; Oeste-Reiss, Sarah. In International Workshop & Tutorial on Interactive Adaptive Learning (IAL). Torino, Italy, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdworking is a popular approach for annotating large amounts of data to train deep neural networks. However, parts of the annotations are often erroneous. In a case study, we demonstrate how an intelligent crowdworker selection via deep learning reduces the number of erroneous annotations and, thus, the annotation costs of obtaining reliable data for training deep neural networks.
Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning. Herde, Marek; Huseljic, Denis; Sick, Bernhard; Bretschneider, Ulrich; Oeste-Reiß, Sarah. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, S. 14–18. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdworking is a popular approach for annotating large amounts of data to train deep neural networks. However, parts of the annotations are often erroneous. In a case study, we demonstrate how an intelligent crowdworker selection via deep learning reduces the number of erroneous annotations and, thus, the annotation costs of obtaining reliable data for training deep neural networks.
The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset. Hetzel, Manuel; Reichert, Hannes; Reitberger, Günther; Doll, Konrad; Sick, Bernhard; Fuchs, Erich. In IEEE Intelligent Vehicles Symposium (IV), S. 1–7. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can cooperate with vehicles, can benefit automated traffic by extending the perception capabilities of drivers and vehicle perception systems. Additionally, they offer the opportunity to gather reproducible and precise data of a holistic scene understanding, including context information as a basis for training algorithms for various applications in automated traffic. Therefore, we introduce the Infrastructural Multi-Person Trajectory and Context Dataset (IMPTC). We use an intelligent public inner-city intersection in Germany with visual sensor technology. A multi-view camera and LiDAR system perceives traffic situations and road users’ behavior. Additional sensors monitor contextual information like weather, lighting, and traffic light signal status. The data acquisition system focuses on Vulnerable Road Users (VRUs) and multiagent interaction. The resulting dataset consists of eight hours of measurement data. It contains over 2,500 VRU trajectories, including pedestrians, cyclists, e-scooter riders, strollers, and wheelchair users, and over 20,000 vehicle trajectories at different day times, weather conditions, and seasons. In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data. The dataset is continuously expanded and is available online for non-commercial research at https://github.com/kav-institute/imptc-dataset
Automatic Textual Explanations of Concept Lattices. Hirth, Johannes; Horn, Viktoria; Stumme, Gerd; Hanika, Tom. In Graph-Based Representation and Reasoning, von Lecture Notes in Computer Science, M. Ojeda-Aciego, K. Sauerwald, R. Jäschke (Hrsg.), S. 138–152. Springer Nature Switzerland, Cham, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Lattices and their order diagrams are an essential tool for communicating knowledge and insights about data. This is in particular true when applying Formal Concept Analysis. Such representations, however, are difficult to comprehend by untrained users and in general in cases where lattices are large. We tackle this problem by automatically generating textual explanations for lattices using standard scales. Our method is based on the general notion of ordinal motifs in lattices for the special case of standard scales. We show the computational complexity of identifying a small number of standard scales that cover most of the lattice structure. For these, we provide textual explanation templates, which can be applied to any occurrence of a scale in any data domain. These templates are derived using principles from human-computer interaction and allow for a comprehensive textual explanation of lattices. We demonstrate our approach on the spices planner data set, which is a medium sized formal context comprised of fifty-six meals (objects) and thirty-seven spices (attributes). The resulting 531 formal concepts can be covered by means of about 100 standard scales.
The Ladder of Participation as a Conceptual Tool for Sustainable Socio-Technical Design of Data-driven Digital Services. Horn, Viktoria; Draude, Claude. In HCI International 2023 Posters, C. Stephanidis, M. Antona, S. Ntoa, G. Salvendy (Hrsg.), S. 60–67. Springer Nature Switzerland, Cham, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Participation in the data economy is prone to unjust power imbalances. Individuals function as mere data sources and are left out of decisions on how, when, and where personal data is accumulated and processed. In this paper, we translate Arnsteins' `Ladder of Citizen Participation' to the field of the data economy to offer a conceptual lens to tackle power imbalances' underlying structures. For this, we derived assumptions from the application's ecosystem. We propose to encase the lowest rungs of the ladder with the term of involuntary participation and frame individuals as digital Citizens to avoid a mere focus on the economic dimension of participation. Building on this, we translate the eight rungs of Arnstein's original ladder to the new application field of the data economy through examples and design affordances corresponding with differing degrees of digital citizens' data agency. Eventually, we contemplate implications for socio-technical design resulting from the re-conceptualization of the `ladder' and formulate future research.
Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets. Huang, Zhixin; He, Yujiang; Herde, Marek; Huseljic, Denis; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, S. 28–45. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Active learning strategies aim to minimize the number of queried samples for model training. However, two challenges in pool-based deep active learning on imbalanced datasets are observed in experiments: (1) the declining performance of active learning strategies due to imbalanced class distribution; (2)~the lack of sample diversity in acquisition batches due to the absence of timely model updates. This paper proposes the AL-FaMoUS, a general solution combining fast model updates and class-balanced minibatch selection to the active learning process. Furthermore, a simplification of the AL-FaMoUS, which selects one single sample in each acquisition minibatch, is experimentally evaluated on four image and three time-series imbalanced datasets. The results demonstrate that the implemented AL-FaMoUS outperforms the other adopted AL strategies, including uncertainty sampling and BALD solely combined with either the fast model update or the class balance selection strategy, in terms of accuracy and Macro F1 score.
Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction. Huang, Zhixin; He, Yujiang; Sick, Bernhard. In Computational Science and Computational Intelligence (CSCI), S. 99–105. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.
Smarter Crowdwork by Applying Smart Contracts? European Conference on Information Systems. Hupe, Anna; Bretschneider, Ulrich. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdworking is characterized by flexibly engaging a workforce that is recruited for only one task. After the task is completed, the crowdworker and the company do not collaborate anymore. To identify the best-suited crowdwoker for a certain task, crowd working platform providers offer different tools to match both parties. Matching a crowdworker with the required skills for a task is an important factor to complete a crowdworking campaign successfully. As of today, the principal agent theorem and high transaction costs decrease the effectiveness of such campaigns due to information asymmetries between crodworkers and crowdsourcers. Based on a qualitative approach, we structurally develop a currently existing crowdworking campaign process. We then theoretically analyze how smart contracts can support and simplify the identified process while reducing the challenges of transaction cost economics and the principal agent theorem.
Revolutionizing Crowdworking Campaigns: Conquering Adverse Selection and Moral Hazard with the Help of Smart Contracts. Hupe, Anna; Bretschneider, Ulrich. In International Conference on Information Systems (ICIS). Hyderabad, India, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdworking is increasingly being applied by companies to outsource tasks beyond their core competencies flexibly and cost-effectively to an unknown group. However, the anonymous and financially incentivized nature of crowdworkers creates information asymmetries and conflicts of interest, leading to inefficiencies and intensifying the principal-agent problem. Our paper offers a solution to the widespread problem of inefficient Crowdworking campaigns. We first derive the currently applied Crowdworking campaign process based on a qualitative study. Subsequently, we identify the broadest adverse selection and moral hazard problems in the process. We then analyze how the blockchain application of smart contracts can counteract those challenges and develop a process model that maps a Crowdworking campaign using smart contracts. We explain how our developed process significantly reduces adverse selection and moral hazard at each stage. Thus, our research provides approaches to make online labor more attractive and transparent for companies and online workers.
Role of Hyperparameters in Deep Active Learning. Huseljic, Denis; Herde, Marek; Hahn, Paul; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, S. 19–24. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Despite considerable research on pool-based deep active learning (DAL), deploying DAL into real applications still has several challenges. A frequently neglected aspect is the choice of training hyperparameters (HPs), such as the learning rate. Since these HPs determine how the deep neural network learns in each cycle, they must be chosen carefully. In this article, we analyze the role of HPs in DAL. We find that optimizing HPs reduces the performance gap between DAL strategies. Conversely, we highlight challenges in finding optimal HPs when using datasets selected via DAL strategies.
Disentangling Trust in Voice Assistants - A Configurational View on Conversational AI Ecosystems. Janson, Andreas; Schmitt, Anuschka; Bevilacqua, Tatjana. In Annual Meeting of the Academy of Management (AOM). Boston, Massachusetts, USA, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
Voice assistants’ (VAs) increasingly nuanced and natural communication via artificial intelligence (AI) opens up new opportunities for the experience of users, providing task assistance and automation possibilities, and also offer an easy interface to digital services and ecosystems. However, VAs and according ecosystems face various problems, such as low adoption and satisfaction rates as well as other negative reactions from users. Companies, therefore, need to consider what contributes to user satisfaction of VAs and related conversational AI ecosystems. Key for conversational AI ecosystems is the consideration of trust due to their agentic and pervasive nature. Nonetheless, due to the complexity of conversational AI ecosystems and different trust sources involved, we argue that we need a more detailed understanding about trust. Thus, we propose a configurational view on conversational AI ecosystems that allows us to disentangle the complex and interrelated factors that contribute to trust in VAs. We examine with a configurational approach and a survey study, how different trust sources contribute to the outcomes of conversational AI ecosystems, i.e., in our case user satisfaction. The results of our study show four distinct patterns of trust source configurations. Vice versa, we show how trust sources contribute to the absence of the outcome, i.e., user satisfaction. The derived implications provide a configurative theoretical understanding for the role of trust sources for user satisfaction that provides practitioners useful guidance for more trustworthy conversational AI ecosystems.
Synthesizing Training Data with Generative Adversarial Networks: Towards the Design of a Data-Sharing Ecosystem Platform for Fraud Detection. Karst, Fabian Sven; Li, Mahei Manhai; Leimeister, Jan Marco. In International Conference on Design Science Research in Information Systems and Technology (DESRIST). Pretoria, South Africa, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
Financial fraud has a severe impact on the general population. While financial institutions have technological capabilities for fraud detection using intelligent AI systems, the delay until they have collected a sufficient size of fraudulent data to train their fraud detection models creates a costly vulnerability. One major challenge for quickly training data lies in the inability to share fraud detection training data with other financial institutions, due to data and privacy regulations. Thus, we create the concept for a data-sharing ecosystem platform that addresses data anonymity concerns by creating synthesized training data based on each institution’s fraud detection training data sets. We rely on the advantages of generative adversarial networks (GAN) to quickly construct a shared dataset for all ecosystem members. Applying design science research, this paper derives design knowledge based on financial fraud detection literature, data sharing between financial institutions, GANs and modular systems theory for the design of a plat-form architecture for data-sharing ecosystems.
Automotive Manufacturers and Their Stumble from one Supply Crisis to Another: Procurement Departments Could be the Game Changer by Using Data Analytics, but…. Klee, Sven; Janson, Andreas; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
With this paper, we examine the use of data analytics for crisis management in automotive procurement departments. Possible business values of data analytics were part of numerous research approaches. Nevertheless, automotive manufacturers are repeatedly confronted with supply chain disruptions. Procurement departments have a central role within supply chains and are predominantly responsible for stable supply processes. Taking into account the potential of data analytics, such crises should be avoided or at least mitigated. Thus, there is the question, why data analytics cannot currently help automotive procurement departments by facing such crises. We therefore evaluate problems and obstacles by implementing and using data analytics in automotive procurement departments. Therefore, we talk to experienced procurement experts for evaluating practical insights. With our findings we provide practical insights and applicable recommendations for action with the goal of helping procurement leaders to better leverage data analytics for meeting current and future crises.
Graph Pooling Provably Improves Expressivity. Lachi, Veronica; Moallemy-Oureh, Alice; Roth, Andreas; Welke, Pascal. In Workshop on New Frontiers in Graph Learning, NeurIPS, S. 1–7. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing layers, can endow hierarchical GNNs with an expressive power regarding the graph isomorphism test that is equal to the Weisfeiler-Leman test. However, the ability of hierarchical GNNs to increase expressive power by utilizing graph coarsening was not yet explored. This results in uncertainties about the benefits of pooling operators and a lack of sufficient properties to guide their design. In this work, we identify conditions for pooling operators to generate WL-distinguishable coarsened graphs from originally WL-indistinguishable but non-isomorphic graphs. Our conditions are versatile and can be tailored to specific tasks and data characteristics, offering a promising avenue for further research.
Establishing a Comprehensive Quality Management for the Use of Crowd-based Mechanisms by SMEs. Lange, Kirsten; Refflinghaus, Robert; Hupe, Anna; Bretschneider, Ulrich. In International Conference on Production Research (ICPR). Cluj-Napoca, Romania, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
This paper describes a concept to adapt the design of quality management in SMEs to better exploit the potential of crowdworking. It shows how the quality management, especially of SMEs, can be organised to make efficient and targeted use of work perfomed by crowd-based mechanisms and continue to ensure that customer requirements are met. The different forms of crowd-based mechanisms will be discussed. Barriers of SMEs in adopting crowdsourcing and strategies to overcome them will be identified. A modular reference process model for the quality-oriented use of crowdworking in SMEs will be developed. In addition, concrete recommendations for action to adapt or supplement the design of quality management in SMEs for the efficient and effective use of crowd-based mechanisms will be given.
Towards the design of hybrid intelligence frontline service technologies – A novel human-in-the-loop configuration for human machine interactions. Li, Mahei Manhai; Löfflad, Denise; Reh, Cornelius; Oeste-Reiß, Sarah. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, 2023.
- [ URL ]
- [ BibSonomy-Post ]
Utilizing Continuous Kernels for Processing Irregularly and Inconsistently Sampled Data With Position-Dependent Features. Magnussen, Birk Martin; Stern, Claudius; Sick, Bernhard. In International Conference on Autonomic and Autonomous Systems (ICAS), S. 49–53. ThinkMind, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces a novel method utilizing continuous kernels for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data natively without additional preprocessing as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with individual failed components without the need for retraining.
Leveraging Repeated Unlabelled Noisy Measurements to Augment Supervised Learning. Magnussen, Birk Martin; Stern, Claudius; Sick, Bernhard. In International Conference on Computational Intelligence and Intelligent Systems (CIIS), S. 1–6. ACM, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Often, producing large labelled datasets for supervised machine learning is difficult and expensive. In cases where the expensive part is due to labelling and obtaining ground truth, it is often comparably easy to acquire large datasets containing unlabelled data points. For reproducible measurements, it is possible to record information on multiple data points being from the same reproducible measurement series, which should thus have an equal but unknown ground truth. In this article, we propose a method to incorporate a dataset of such unlabelled data points for which some data points are known to be equal in end-to-end training of otherwise labelled data. We show that, with the example of predicting the carotenoid concentration in human skin from optical multiple spatially resolved reflection spectroscopy data, the proposed method is capable of reducing the required number of labelled data points to achieve the same prediction accuracy for different model architectures. In addition, we show that the proposed method is capable of reducing the negative impact of noisy data when performing a repeated measurement of the same sample.
Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network. Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Nather, Rüdiger; Thomas, Josephine. In Workshop on Temporal Graph Learning (TGL), NeurIPS, S. 1–7. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.
Towards Few-Shot Time Series Anomaly Detection with Temporal Attention and Dynamic Thresholding. Nivarthi, Chandana Priya; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), S. 1444–1450. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Anomaly detection plays a pivotal role in diverse realworld applications such as cybersecurity, fault detection, network monitoring, predictive maintenance, and highly automated driving. However, obtaining labeled anomalous data can be a formidable challenge, especially when anomalies exhibit temporal evolution. This paper introduces LATAM (Long short-term memory Autoencoder with Temporal Attention Mechanism) for few-shot anomaly detection, with the aim of enhancing detection performance in scenarios with limited labeled anomaly data. LATAM effectively captures temporal dependencies and emphasizes significant patterns in multivariate time series data. In our investigation, we comprehensively evaluate LATAM against other anomaly detection models, particularly assessing its capability in few-shot learning scenarios where we have minimal examples from the normal class and none from the anomalous class in the training data. Our experimental results, derived from real-world photovoltaic inverter data, highlight LATAM’s superiority, showcasing a substantial 27% mean F1 score improvement, even when trained on a mere two-week dataset. Furthermore, LATAM demonstrates remarkable results on the open-source SWaT dataset, achieving a 12% boost in accuracy with only two days of training data. Moreover, we introduce a simple yet effective dynamic thresholding mechanism, further enhancing the anomaly detection capabilities of LATAM. This underscores LATAM’s efficacy in addressing the challenges posed by limited labeled anomalies in practical scenarios and it proves valuable for downstream tasks involving temporal representation and time series prediction, extending its utility beyond anomaly detection applications.
Transferring Well-Performing Collaborative Work Practices with Parameterized Templates and Guidebooks: Empowering Subject Matter Experts for an Adaptation to Slightly Different Contexts. Oeste-Reiß, Sarah; Söllner, Matthias; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Collaborative work practices (CWPs) package facilitation expertise and have the potential to increase team productivity up to 90%. Collaboration engineers develop CWPs and deploy them to practitioners that execute them. These CWPs, however, are typically customized to conditions of a specific use case. This creates the challenge that changing use case conditions or even small variations across contexts, hinder well-performing CWPs of being applied more often to create a long-term value. Practitioners fail to adapt existing CWPs due to missing collaboration expertise and adaptation guidelines. To address this challenge in collaboration engineering literature, we introduce a) the Subject Matter Expert role; b) the ‘CWP Adaptation Approach’ that formalizes the transfer of CWPs to different contexts with parameterized Templates and Guidebooks. To show a first proof-of-concept, we further inductively generalize from an exemplarily use case with a well-performing CWP in the educational domain.
Collaborative Work Practices for Management Education: Using Collaboration Engineering to Design a Reusable and Scalable Collaborative Learning Instructional Design. Oeste-Reiß, Sarah; Söllner, Matthias; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICCS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Pandemics like COVID-19 highlight the needs and pitfalls of inclusive and equitable education in a digital society. IT-based instructional designs are needed to increase learners’ expertise, and to develop higher-order thinking skills. Instructional designs for collaborative learning (CL) seem to be a promising solution. However, they are mostly suitable for face-to-face and not for distance teaching. The core problem that impedes their reusability and scalability is a ‘collaboration problem’ for which collaboration engineering (CE) provides guidance. Therefore, we deploy a design science research study and contribute to CL and CE literature. We develop requirements and provide the design of an IT-based collaborative work practice fostering CL. We provide empirical evidence with an online experiment in a large-scale lecture with undergraduate business information students. This reveals that groups of learners who followed our CL experience achieve higher levels of expertise than those who followed a traditional ad hoc CL experience.
Individualizing Patient Pathways through Modularization: Design and Evaluation of Healthcare-Specific Modularization Parameters. Peters, Christoph; Richter, Peggy. In Proceedings of the 56th Hawaii International Conference on System Sciences (HICSS 2023). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Some classes of person-oriented services such as healthcare services require individualization to be effective. Individualizing services and corresponding patient pathways are costly. To provide such services in an individualized, but also efficient manner, service modularization is known as a solution. Until now, modularization parameters that take healthcare specificities into account are missing. This paper closes this gap. Following a design science research approach, we iteratively build and evaluate a set of healthcare-specific modularization parameters. For requirements elicitation, refinement of the modularization parameters and their evaluation, we conduct interviews with domain experts from patient pathways in oncology care as well as with service design and business development experts. As main theoretical contribution, this paper provides design knowledge for the modularization of healthcare services. For practice, the set of parameters assists healthcare providers in the efficient provision of individualized, patient-centric solutions and patient pathways.
Designing for Digital Wellbeing on a Smartphone: Co-creation of Digital Nudges to Mitigate Instagram Overuse. Purohit, Aditya Kumar; Barev, Torben Jan; Schöbel, Sofia; Janson, Andreas; Holzer, Adrian. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The endless stream of social media newsfeeds and stories captivates users for hours on end, sometimes exceeding what users themselves consider unhealthy. However, reducing one's social media consumption has proven to be challenging. To address this issue, this study investigates how the co-creation of the digital feedback nudge can improve digital well-being without increasing privacy threats. To achieve this goal, a mixed method study is used through a two-week pre-post study design. Results demonstrate that co-creation significantly increased users' sense of agency, sense of accomplishment and perceived sense of privacy while reducing users' privacy concern. Furthermore, the feedback nudge allowed participants to significantly decrease their social media use.
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers. Rauch, Lukas; Aßenmacher, Matthias; Huseljic, Denis; Wirth, Moritz; Bischl, Bernd; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), S. 55–74. Springer, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.
Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers. Rauch, Lukas; Schwinger, Raphael; Wirth, Moritz; Sick, Bernhard; Tomforde, Sven; Scholz, Christoph. In Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI, S. 1–6. 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.
Sensor Equivariance by LiDAR Projection Images. Reichert, Hannes; Hetzel, Manuel; Schreck, Steven; Doll, Konrad; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), S. 1–6. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view. To that end, we propose an architecture for processing this data in an instance segmentation framework. We focus specifically on LiDAR as a key sensor modality for machine vision tasks and highly automated driving (HAD). Through an experimental setup in a controlled synthetic environment, we identify a bias on sensor resolution and field of view and demonstrate that our proposed method can reduce said bias for the task of LiDAR instance segmentation. Furthermore, we define our method such that it can be applied to other projection-based sensors, such as cameras. To promote transparency, we make our code and dataset publicly available. This method shows the potential to improve performance and robustness in various machine vision tasks that utilize projection-based sensors.
Empowering Recommender Systems in ITSM: A Pipeline Reference Model for AI-based Textual Data Quality Enrichment. Reinhard, Philipp; Li, Mahei Manhai; Dickhaut, Ernestine; Peters, Christoph; Leimeister, Jan Marco. In International Conference on Design Science Research (DESRIST), A. Gerber, R. Baskerville (Hrsg.). Pretoria, South Africa, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
AI-based recommendation systems to augment working conditions in the field of IT service management (ITSM) have attracted new attention. However, many IT support organizations possess high volumes of tickets but are confronted with low quality, to which they train the underlying models of their AI systems. In particular, support tickets are documented insufficiently due to time pressure and lack of motivation. Following design science research, we design and evaluate an analytics pipeline to address the data quality issue. The pipeline can be applied to assess and extract high-quality support tickets for subsequent model training and operation. Based on a data set of 60.000 real-life support tickets from a manufacturing company, we develop the artifact, instantiate a recommender system and achieve a higher pre-diction performance in comparison to naïve enrichment methods. In terms of data management literature, we contribute to the understanding of as-sessing textual ticket data quality. By deriving a pipeline reference model, we move towards a general approach to designing machine learning-driven data quality analytics pipelines for attached recommender systems.
A Conceptual Model for Labeling in Reinforcement Learning Systems: A Value Co-Creation Perspective. Reinhard, Philipp; Li, Mahei Manhai; Dickhaut, Ernestine; Reh, Cornelius; Peters, Christoph; Leimeister, Jan Marco. In International Conference on Design Science Research (DESRIST), A. Gerber, R. Baskerville (Hrsg.). Pretoria, South Africa, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Artificial intelligence (AI) possesses the potential to augment customer service employees e.g. via decision support or solution recommendations. Still, its underlying data for training and testing the AI systems is provided by human annotators through human-in-the-loop configurations. However, due to the high effort for annotators and lack of incentives, AI systems face low underlying data quality. That in turn results in low prediction performance and limited acceptance by the targeted user group. Faced with the enormous volume and increasing complexity of service requests, IT service management (ITSM) especially, relies on high data quality for AI systems and in-corporating domain-specific knowledge. By analyzing the existing labeling process in that specific case, we design a revised to-be process and develop a conceptual model from a value co-creation perspective. Finally, a functional prototype as an instantiation in the ITSM domain is implemented and evaluated through accuracy metrics and user evaluation. The results show that the new process increases the perceived value of both labeling quality and the perceived prediction quality. Thus, we contribute a conceptual model that supports the systematic design of efficient and interactive labeling processes in diverse applications of reinforcement learning systems.
Towards designing an AI-based conversational agent for on-the-job training of customer support novices. Reinhard, Philipp; Wischer, Dennis; Verlande, Lisa; Neis, Nicolas; Li, Mahei Manhai. In International Conference on Design Science Research (DESRIST). Pretoria, South Africa, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Due to the high drop-out rates in IT support desks, efficient onboarding of novices becomes a relevant and recurring challenge. Especially in the case of IT support, solving technical issues and service requests while the conversation with the customer is still ongoing imposes high demands on novice support agents. As artificial intelligence (AI) can already classify service requests and help find solutions, AIbased augmentation holds great potential for improving the onboarding phase and reducing time-to-performance. For this reason, we propose an AI-based conversational (co-)agent during the onboarding phase of customer support novices to reduce the time spent on service tasks and enable on-the-job training. Following action design research, we aim to develop an instantiation of an AI-based co-agent to reduce the job demand for the service center agent novices and augment problem-solving capabilities by considering cognitive load. The co-agent will be implemented with one development partner and evaluated with two different case partner organizations. In this research-in-progress project, we developed a low-fidelity prototype and derived a tentative architecture that allows for a generalized development of such conversational agents in customer service organizations.
GETTING INTO FLOW!? ENHANCE FLOW-LIKE EXPERIENCES AND LEARNING PERFORMANCE THROUGH PERSONALIZED LEARNING ACTIVITIES. Ritz, Eva. In European Conference on Information Systems (ECIS). Kristiansand, Norway, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Although intelligent learning systems provide new opportunities for personalizing learning activities, important design questions remain. To unleash the full impact of such systems, it is vital to examine how the use of Bayesian knowledge tracing can provide learners personalized learning activities and shape their flow experience, performance, and continuity intention. Further, this study explores the moderating role of a growth mindset on the relation between learning task adaptation and flow experience. I rely on electroencephalography to increase the internal validity of flow measurements. The study builds on Flow Theory and aims to empirically unveil the influence of an intelligent personalization of learning processes. The next step will be an experiment with 80 participants following the developed experimental design to evaluate flow experiences in intelligent learning systems. The results of this experiment aim to guide educational designers with prescriptive knowledge on how to design flow-like learning experiences in intelligent learning systems.
Artificial Socialization? How Artificial Intelligence Applications Can Shape A New Era of Employee Onboarding Practices. Ritz, Eva; Fabio, Donisi; Elshan, Edona; Rietsche, Roman. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Onboarding has always emphasized personal contact with new employees. Excellent onboarding can extend employee retention and improve loyalty. Even in a physical setting, the onboarding process is demanding for both the newcomer and the onboarding organization. Remote work, in contrast, has made this process even more challenging by forcing a rapid shift from offline to online onboarding practices. Organizations are adopting new technologies like artificial intelligence (AI) to support work processes, such as hiring processes or innovation facilitation, which could shape a new era of work practices. However, it has not been studied how AI applications can or should support onboarding. Therefore, our research conducts a literature review on current onboarding practices and uses expert interviews to evaluate AI's potential and pitfalls for each action. We contribute to the literature by presenting a holistic picture of onboarding practices and assessing potential application areas of AI in the onboarding process.
Time-aware Robustness of Temporal Graph Neural Networks for Link Prediction. Sälzer, Marco; Beddar-Wiesing, Silvia. In International Symposium on Temporal Representation and Reasoning (TIME), S. 19:1–19:3. 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Graph Neural Networks (GNNs) provide a framework for computing functions over graphs based on learnable parameters, which gained much attention in recent years. The most popular GNN models, so-called convolutional GNN or message-passing GNN apply a neighborhood aggregation procedure to each node in a graph to compute its output. Usually, such GNNs are used for classification or prediction tasks over static graphs. However, this limits their applicability in contexts like social networks or knowledge graphs, where underlying graphs change stepwise or time-continuously. Temporal Graph Neural Networks (TGNN) try to close this gap. The general idea of TGNN is to generalize the neighborhood aggregation procedure mentioned above to temporal graphs, usually represented as a tuple of a base graph with a series of time-stamped observed changes. In most applications involving Neural Network based models, giving reliable safety certificates are highly desirable but also a significant challenge, especially because of the blackbox nature of neural models. In this extended abstract, we address the topic of verifying TGNN, which is an unexplored area of research. We present a first notion of a time-aware robustness property for TGNN used for link prediction tasks, motivated by recent work on similar time-aware attacks. Furthermore, we discuss our ongoing work regarding promising verification approaches for the presented or similar safety properties and possible next steps in this research direction.
Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy. Sandrock, Christoph; Herde, Marek; Kottke, Daniel; Sick, Bernhard. In Discovery Science (DS), S. 265–276. Springer, 2023.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Active learning aims to reduce the amount of labeled data while maximizing machine learning models’ performances. Currently, there is sparse research on the potential of an optimal active learning strategy. Therefore, we propose a non-myopic oracle policy that accesses the true labels of the data pool to approximate an optimal active learning strategy. We evaluate how the hyperparameters of this oracle policy influence its performance and empirically demonstrate that it is an upper baseline for common active learning strategies while being faster than a state-of-the-art oracle policy. For the sake of reproducibility, all the code related to our research is publicly available on our GitHub repository at https://github.com/ies-research/non-myopic-oracle-policy.
Social Audio: Conceptualizing Voice-Based Online Social Networks and their Privacy Implications. Schmitt, Anuschka; Rentsch, Stefanie; Janson, Andreas. In Annual Meeting of the Academy of Management (AOM). Boston, Massachusetts, USA, 2023.
- [ Abstract ]
- [ BibSonomy-Post ]
This paper explores the nature and implications of social audio: online social networks (OSNs) that enable users to interact via voice. The paper contributes to basic science by offering a precise conceptualization of voice-based OSNs and their design features. We posit that the defining characteristics of traditional OSNs also hold for social audio, yet that novel features (i.e., creating rooms) and modifications of traditional features (i.e., like) through voice idiosyncrasies can be found. This work also shows how social audio introduces novel privacy implications, particularly driven by the richness and risks of voice as an interaction modality. Using three illustrative cases, we demonstrate applications of social audio and how privacy implications remain largely unaddressed. Specifically, we find that the networks considered show very few specific features addressing the risks of voice-based interaction and that current privacy policies do not reflect these risks nor offer mitigation measures. We bridge our findings and extensions for future research by discussing potential approaches in terms of network architecture features for social audio providers to pursue in order to ensure user privacy.
Not everything is a Metaverse?! A Practitioners Perspective on Characterizing Metaverse Platforms. Schöbel, Sofia; Karatas, Jasmin; Tingelhoff, Fabian; Leimeister, Jan Marco. In Proceedings of the Hawaii International Conference of System Science (HICSS), Bd. 56. Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Organizations claim to host what is called a metaverse – an extended version of our real world. First rudimental realizations of such metaverses can be found throughout the internet, e.g., Epic Game’s Fortnite. At the same time, research and practice struggle to specify what a metaverse truly is and how we can characterize it. With our work, we analyze the proximity of the realization of a holistic metaverse platform and present the results of a qualitative interview study (n=30). The goal of our work is to use the expertise of practitioners to discuss different examples that claim to represent a metaverse, e.g., Second Life and Decentraland. To achieve this goal, we develop a typology we call the Metagon and use it to evaluate existing metaverse platforms. We contribute to theory by clarifying the meaning of metaverse platforms. Practitioners are guided by a demonstration of metaverse characteristics.
Height Change Feature Based Free Space Detection. Schreck, Steven; Reichert, Hannes; Hetzel, Manuel; Doll, Konrad; Sick, Bernhard. In International Conference on Control, Mechatronics and Automation (ICCMA), S. 171–176. IEEE, 2023.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
We present a novel method for free space detection in dynamic environments like factory sites, crucial for autonomous forklifts to avoid collisions. It introduces a technique for fast surface normal estimation using spherical projected LiDAR data, which helps in detecting free space efficiently and in real-time. The method's effectiveness is proven with a 50.90% mIoU score on the Semantic KITTI dataset at 105 Hz, and a 63.30% mIoU score on a factory site dataset at 54 Hz.
The Mont Blanc of Twitter: Identifying Hierarchies of Outstanding Peaks in Social Networks. Stubbemann, Maximilian; Stumme, Gerd. In Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part III, Bd. 14171 von Lecture Notes in Computer Science, S. 177–192. Springer, 2023.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Mechanisms of Common Ground in Human-Agent Interaction: A Systematic Review of Conversational Agent Research. Tolzin, Antonia; Janson, Andreas. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Human-agent interaction is increasingly influencing our personal and work lives through the proliferation of conversational agents in various domains. As such, these agents combine intuitive natural language interactions by also delivering personalization through artificial intelligence capabilities. However, research on CAs as well as practical failures indicate that CA interaction oftentimes fails miserably. To reduce these failures, this paper introduces the concept of building common ground for more successful human-agent interactions. Based on a systematic review our analysis reveals five mechanisms for achieving common ground: (1) Embodiment, (2) Social Features, (3) Joint Action, (4) Knowledge Base, and (5) Mental Model of Conversational Agents. On this basis, we offer insights into grounding mechanisms and highlight the potentials when considering common ground in different human-agent interaction processes. Consequently, we secure further understanding and deeper insights of possible mechanisms of common ground in human-agent interaction in the future.
Designing Pedagogical Conversational Agents for Achieving Common Ground. Tolzin, Antonia; Körner, Anita; Dickhaut, Ernestine; Janson, Andreas; Rummer, Ralf; Leimeister, Jan Marco. In International Conference on Design Science Research (DESRIST). Pretoria, South Africa, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
As educational organizations face difficulties in providing personalized learning material or individual learning support, pedagogical conversational agents (PCAs) promise individualized learning for students. However, the problem of conversational breakdowns of PCAs and consequently poor learning outcomes still exist. Hence, effective and grounded communication between learners and PCAs is fundamental to improving learning processes and out-comes. As understanding each other and the conversational grounding is crucial for conversations between humans and PCAs, we propose common ground theory as a foundation for designing a PCA. Conducting a design science research project, we propose theory-motivated design principles and instantiate them in a PCA. We evaluate the utility of the artifact with an experimental study in higher education to inform the subsequent design iterations. We contribute design knowledge on conversational agents in learning settings, enabling researchers and practitioners to develop PCAs based on common ground research in education and providing avenues for future research. Thereby, we can secure further understanding of learning processes based on grounding communication.
Introduction to the Minitrack on Digital Service and Service Digitalization. Tuunanen, Tuure; Böhmann, Tilo; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2023.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The purpose of the minitrack is to attract research on the innovation, design, development, management, and use of digital services and the digitalization of services. The key drivers in this area of research are the multiplying technological opportunities for digital services, such as ubiquitous connectivity, artificial intelligence, wearable devices, cyber-physical systems, Internet of Things (IoT), virtual/augmented reality, web3, and so on. The minitrack provides a discussion forum for researchers interested in theoretical and practical problems related to such services (Huang & Rust, 2013; Lusch & Nambisan, 2015).

2022[ to top ]

Empowerment Effects in Human-machine Collaboration - A Systematic Literature Review and Directions on Hybrid Intelligence Behavior Patterns. Akmeikina, Elisabeth; Eilers, Karen; Li, Mahei Manhai; Peters, Christoph. In Pacific Asia Conference on Information Systems (PACIS). Taipei/Sidney, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The potentials of artificial intelligence (AI) are manifold and their discussion has gained momentum in research and practice. In the same realm, AI also raises fears among employees of being replaced by AI technologies and, therefore, shying away from using it. Generally, employees want to be empowered to do their job and seek both more responsibility, as well as make their own decisions. In this paper, we conduct a systematic literature review that investigates the current state of the literature on the potential empowering effects of AI-based human-machine behavior. We thus sorted the literature into three behavioral categories: humans shape machine behavior, machines shape human behavior, human-machine co-behavior and crossed them with psychological empowerment dimensions of significance, competence, self-determination, and influence. Our results show corresponding literature streams and provide future research directions in a field that is likely to disrupt the way we work in the future.
Heterogeneous Multi-Source Deep Adaptive Knowledge-Aware Learning for E-Mobility. Ali, Mohammad Wazed. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), S. 57–60. IEEE, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Electromobility (e-mobility) reduces global fossil fuel-based energy demand and promotes the usage of renewable energy sources. Different types of electric vehicle (EVs) production have increased recently due to their need. However, there is no fixed charging behavior, and demand exists. Uncontrolled EV charging may lead to a harmful impact on the power grid. Besides, most renewable energy sources depend highly on the weather and location. Thus, analyzing, forecasting, and adapting EV charging demand is essential to prevent power outages. Deep Learning (DL) models are a de facto standard technology for energy forecasting in many scenarios. Still, there is a lack of real-world data in the e-mobility domain to train a DL model from scratch. Besides, DL models have explainability issues, which can hinder decision-making. This article proposes a novel framework for addressing data scarcity issues, enabling continuous adaptation to change, and improving explainability.
Collision Avoidance for Vulnerable Road Users: Privacy versus Survival?. Bachmann, M.; Acosta, L. H.; Götz, J.; Reinhardt, D.; David, K. In 5th International Workshop on Intelligent Transportation and Autonomous Vehicles Technologies (ITAVT 2022) in conjunction with IEEE/IFIP Network Operations and Management Symposium (NOMS 2022), S. 1–6. 2022.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs. Beddar-Wiesing, Silvia. In ACM/SIGAPP Symposium on Applied Computing (SAC), S. 604–609. ACM, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Graphs have recently become more popular for modeling real-world as well as theoretical problems, and several Machine Learning algorithms for learning on them have developed. For graphs that change over time, however, research is still at an early stage. This article proposes a framework DynHeatmaP that generates a constant-size graph sequence representation of graphs whose structure changes over time (structural-dynamic, SDG) in linear time. The framework uses a representation of additions and deletions of nodes and edges (events) to perform dynamic graph pooling. Our algorithm translates the dynamic changes of the nodes and edges to a heatmap representation of the current node activity, regarding additions and deletions in the neighborhood, respectively. The created activity heatmap is utilized as probabilities of the nodes to be sampled in the subsequent pooling step. In addition, the neighborhood of selected nodes has been sampled such that the ratio of additions and deletions is represented accordingly. The obtained downsampled graph sequence can then be used representatively as input to a GNN for learning on the original stream. Focussing on the active regions in a graph, the fast pooling process can reduce the training time significantly and addresses the problem of unbalanced datasets in real-world applications modeled as sparse graphs.
On the Extension of the Weisfeiler-Lehman Hierarchy by WL Tests for Arbitrary Graphs. Beddar-Wiesing, Silvia; D’Inverno, Giuseppe Alessio; Graziani, Caterina; Lachi, Veronica; Moallemy-Oureh, Alice; Scarselli, Franco. In Workshp on Mining and Learning on Graphs (MLG), ECML PKDD, S. 1–13. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Graph isomorphism (GI) has occupied both theoreticians and applied scientists since the early 1950s. Over the years, several approaches and algorithms with which an isomorphism between two graphs can be tested have been developed. A general approach is the Weisfeiler–Lehman (WL) test, which is based on a coloring algorithm and provides a necessary criterion for graph isomorphism. However, the WL test is restricted to examining graphs with only node attributes. Therefore, this paper presents two extensions of the WL algorithm to allow for testing on arbitrary graphs. One considers edge attributes, and the other tests the isomorphism on dynamic graphs. Additionally, we extend the WL-hierarchy by the attributed and dynamic WL tests and show that it is a partial order, which induces a lattice. In the future, this may allow for practical implications coming from lattice theory.
Can you help me scale? A Systematic Analysis of Scaling Capabilities of Conversational Agents for Digital Services. Benner, Dennis; Schöbel, Sofia; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Wirtschaftsinformatik (WI). 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Today’s servitized and digitalized society has significant implications for the economic system as value creation increasingly shifts towards digital services. Organizations are increasingly relying of artificial intelligence, which enables them to operate with novel technological artifacts like conversational agents (CA). These human-like AI-driven artifacts open new possibilities and channels for service providers to scale up their business even further and to create a business value or even to make processes more efficient. While we witness the results of that each day, we do not fully understand how such CAs can contribute to scaling up a business. Therefore, we conduct an analysis of service research and popular CAs to determine the status quo and highlight opportunities for scaling services with CAs. We contribute to theory by clarifying the meaning of scalability in combination with CAs and support practitioners by providing an overview about how organizations successfully scale their CAs.
Towards Gamified Conversational Agents for Self-Regulated Learning in Digital Education. Benner, Dennis; Schöbel, Sofia; Sueess, Christoph. In International Conference on Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Formal education like higher education oftentimes emphasized on strict non-digital setting. This approach can lead to issues during stressful times (e.g., Covid crisis) or when learners’ needs in general are not considered. Moreover, these times highlighted how important self-regulated learning is and how much this capability is lacking in our educational system. To address these issues, we follow an Action Design Research approach and develop a gamified conversational agent (CA) that considers the learners’ needs. We present our CA and conduct a first small-scale evaluation following a mixed-method approach. First results show that students universally liked a CA for self-regulated digital learning and many enjoyed the gamified experience which helped students to be motivated to learn. As next steps we will develop the next iteration of our CA and conduct a long-term field test at a university.
Level-Up your Learning - Introducing a Framework for Gamified Educational Conversational Agents. Benner, Dennis; Schöbel, Sofia; Süess, Christoph; Baechle, Vera; Janson, Andreas. In International Conference on Wirtschaftsinformatik (WI). 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Driven by circumstances like the global pandemic many learners and educators realize the importance and value of self-regulated digital learning. To better support self-regulated learning, conversational agents have become more relevant. Conversational agents can act as tutor or as learning mate for learners. Although conversational agents have potential to better support self-regulated learning processes, challenges exist requiring implications about how to make these interactions more engaging and supportive. This study discusses the value of gamified conversational learning chatbots that use game elements to engage learners to guide researchers and practitioners to design conversational agents that effectively motivate learners and provide self-regulated learning at the same time. Therefore, we propose a systematically developed framework for gamifying educational conversational agents and contribute to theory by consolidating several theories about games, digital learning, and conversational agents and support practitioners by providing implications about what to care about when gamifying conversational agents.
Natural Language Processing (NLP) und der Datenschutz - Chancen und Risiken für den Schutz der Privatheit. Choi, J.-E.; Setz, T.; Steinebach, M.; Vogel, I. In INFORMATIK 2022, D. Demmler, D. Krupka, H. Federrath (Hrsg.), S. 651–664. Gesellschaft für Informatik, Bonn, 2022.
- [ BibSonomy-Post ]
What should AI know? Information disclosure in human-AI collaboration. Cvetkovic, Izabel; Oeste-Reiß, Sarah; Lehmann-Willenbrock, Nale; Bittner, Eva. In European Conference on Information Systems (ECIS). Timisoara, Romania, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
AI-assisted Design Thinking shows great potential for supporting collaborative creative work. To foster creative thinking processes within teams with individualized suggestions, AI has to rely on data provided by the teams. As a prerequisite, team members need to weigh their disclosure preferences against the potential benefits of AI when disclosing information. To shed light on these decisions, we identify relevant information such as emotional states or discussion arguments that design thinking teams could provide to AI to enjoy the benefits of its support. Using the privacy calculus as theoretical lens, we draft a research design to analyze user preferences for disclosing different information relevant to the service bundles that AI provides for respective information. We make explorative contributions to the body of knowledge in terms of AI use and its corresponding information disclosure. The findings are relevant for practice as they guide the design of AI that fosters information disclosure.
NDNET: A Unified Framework for Anomaly and Novelty Detection. Decke, Jens; Schmeißing, Jörn; Botache, Diego; Bieshaar, Maarten; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), S. 197–210. Springer, 2022.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
We introduce NDNET (https://novelty-detection.net/p/ndnet), an anomaly and novelty detection library that implements various detection algorithms adjusted for online processing of data streams. The intention of this library is threefold: 1) Make experimentation with different anomaly and novelty detection algorithms simple. 2) Support the development of new novelty detection approaches by providing the mCANDIES framework. 3) Provide fundamentals to analyze and evaluate novelty detection algorithms on data streams. The library is freely available and developed as open-source software.
Conceptualizing Design Knowledge in IS Research – A Review and Taxonomy of Design Knowledge Properties. Dickhaut, Ernestine; Janson, Andreas; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS), S. 5778–5787. Hawaii, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Design science projects are of great interest in information systems (IS) research. Typically, design-oriented projects generate valuable design knowledge through the design and possible instantiation of artifacts. Although designing novel artifacts and accumulating design knowledge is common practice in IS, there is still limited shared knowledge about the distinctive characteristics of design knowledge to facilitate its accumulation. To address this issue, we develop a design knowledge taxonomy and contribute to a deeper understanding of design knowledge properties. The taxonomy is grounded on a systematic literature review, followed by a combination of empirical-to-conceptual and conceptual-to-empirical iterations. We evaluate the taxonomy by interviewing six domain experts and demonstrate its practical application and utility. Thus, the taxonomy consists of key dimensions and characteristics of design knowledge and contributes to a better scientific understanding of its characteristics. Practitioners can use the taxonomy as an instrument to further understand, design, and accumulate design knowledge.
Analyzing Design Knowledge Representation in Design Science Research and Deriving Recommendations to Support Design Knowledge Codification. Dickhaut, Ernestine; Janson, Andreas; Leimeister, Jan Marco. In The Transdisciplinary Reach of Design Science Research. 17th International Conference on Design Science Research in Information Systems and Technology (DESRIST), Bd. 13229 von Lecture Notes in Computer Science, A. Drechsler, A. Gerber, A. Hevner (Hrsg.), S. 417–428. St. Petersburg, Florida, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
The goal of design science research is the generation of novel artifacts. Thereby DSR projects generate valuable design knowledge, thus, underscoring the importance to codify of design knowledge for achieving scientific progress. The research community observes that DSR projects generate a large amount of design knowledge, but the developed knowledge often ends as a single success story. To counter this situation, we analyze the variety of design knowledge representation forms that have been published in the AIS Senior Scholars’ Basket in design science research papers. Based on our systematic literature review, we identify prevalent ways of design knowledge representations. We provide as a central contribution how to effectively communicate design knowledge through the derivation of recommendations that provides practical guidance to support researchers and practitioners in making design knowledge contributions reusable and applicable.
Introducing Conversational Explanations as a Novel Response Strategy to Data Breach Incidents in Digital Commerce. Diesterhöft, Till Ole; Benner, Dennis; Brauer, Benjamin. In pre-ICIS Workshop on Information Security and Privacy (WISP). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In order to individualize and personalize digital services, an increasing number of e-commerce providers are exploiting abundant amounts of customer information. Alongside these positive effects, an inherent risk of compromise of customer information arises, resulting in data breaches. Compelled by regulations, companies are obliged to notify their customers. Previous literature indicates that different data breach response strategies can mitigate the negative effects of these security incidents. Drawing on data breach and conversational agent (CA) research, we theorize that the manner in which a data breach is communicated is equally relevant. We test our developed hypotheses in an online experiment (n=89). Our results show that explaining a data breach increases customer satisfaction. Simultaneously, we reveal that CAs lend themselves as a tool to positively influence this degree of explanation. Our work provides novel insights into the centrality of explanation in a data breach response and their positive correlation with CAs.
Hybrid Spaces, Hybrid Methodologies: Finding Ways of Working with Social Sciences and Humanities in Human-Computer Interaction. Draude, Claude; Klumbytė, Goda. In Human-Computer Interaction. Theoretical Approaches and Design Methods, Bd. 13302 von Lecture Notes in Computer Science, M. Kurosu (Hrsg.), S. 40–56. Springer International Publishing, Cham, 2022.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Starting from the need for responsible research and innovation in computing, this paper addresses the challenges that come from working with the social sciences and the humanities in human-computer interaction. In this paper, we attempt to move beyond interdisciplinarity towards transdisciplinarity. In particular, we explore concepts of hybridity and third spaces that are used in HCI participatory design practices. We trace back the postcolonial, decolonial and feminist scholarship basis of these concepts and look at how their critical potential can inform a conceptualization of what we call hybrid methodology in its own right. For this, we present three case studies. The first two work with experimental spaces in artistic research and research through design, the third works with intersectional critical and speculative methodologies in machine learning systems design. The first two case studies center around the discussions of disciplinary openness through experimentation as a way of moving beyond interdisciplinarity towards transdisciplinarity; the third zooms in on the role of critical theoretical knowledge from the social sciences and the humanities as knowledge that enables new orientations in research and design of IT systems.
Requirements for AI-based Teammates: A Qualitative Inquiry in the Context of Creative Workshops. Elshan, Edona; Siemon, Dominik; de Vreede, Triparna; de Vreede, Gert-Jan; Oeste-Reiß, Sarah; Ebel, Philipp. In Hawaii International Conference on System Sciences (HICSS). 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Innovation requires organizations to tap into the knowledge and creativity of teams. However, teams are confronted with massive amounts of data and information, necessitating a broad set of knowledge, methodologies, and approaches to solve problems and innovate. Consequently, team composition has become a critical challenge. Recent advances in artificial intelligence (AI) may assist in addressing this challenge. As AI is permeating both business and private sectors, organizational teams may be augmented with AI team members. However, given the nascent nature of this phenomenon, little is known about the specific roles and requirements for such AI teammates. Within an interview study we discover common challenges in teams and identify recurring capability gaps of participants and behaviors that negatively impact the team's collective performance. Based on our findings, we propose requirements for AI-based teammates to address these gaps and support beneficial collaboration between humans and AI in teams.
Priority-Dependent Display of Notifications in the Peripheral Field of View of Smart Glasses. Faulhaber, A. K.; Hoppe, M.; Schmidt, L. In 28th IEEE Conference on Virtual Reality and 3D User Interfaces: Abstracts and Workshops (Christchurch 2022), S. 586–587. IEEE, Piscataway, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
We propose a concept for displaying notifications in the peripheral field of view of smart glasses aiming to achieve a balance between perception and distraction depending on the priority of the notification. We designed three different visualizations for notifications of low, medium, and high priority. To evaluate this concept, we conducted a study with 24 participants who reacted to the notifications while performing a primary task. Reaction times for the low-priority notification were significantly higher. The medium- and high-priority notifications did not show a clear difference.
Attribute Exploration with Multiple Contradicting Partial Experts. Felde, Maximilian; Stumme, Gerd. In Graph-Based Representation and Reasoning, T. Braun, D. Cristea, R. Jäschke (Hrsg.), S. 51–65. Springer International Publishing, Cham, 2022.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Attribute exploration is a method from Formal Concept Analysis (FCA) that helps a domain expert discover structural dependencies in knowledge domains which can be represented as formal contexts (cross tables of objects and attributes). In this paper we present an extension of attribute exploration that allows for a group of domain experts and explores their shared views. Each expert has their own view of the domain and the views of multiple experts may contain contradicting information.
Commonsense Knowledge for Human-Robot Collaboration in Hybrid Search and Rescue Teams. Geihs, Kurt; Jakob, Stefan; Opfer, Stephan; Alhamwy, Yasin. In 2nd International Workshop on Human-Robot Interaction: New Trends in Service and Industry (HRI-SI2022). Naples/Italy, 2022.
- [ BibSonomy-Post ]
Self-Aware Microsystems. Gruhl, Christian; Tomforde, Sven; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 126–127. IEEE, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Besides infrastructure-based solutions, small-scale microsystems are increasingly connected and interoperating with others in changing environments. Following the same motivation as for self-adaptive systems, this demands novel attempts to counter complexity and provide autonomous decision freedom that paves the path towards resilient and flexible behaviour. In this article, we outline a vision for research on self-aware microsystems (SAM) that aims at providing technical solutions that are especially relevant for initiatives such as self-improving system integration.
Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning. He, Yujiang; Huang, Zhixin; Sick, Bernhard. In Workshop on Interactive Machine Learning Workshop (IMLW), AAAI, S. 1–6. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general challenges should be overcome in further research before we apply this technique to real-world applications. Firstly, newly collected novelties from the data stream in applications could contain anomalies that are meaningless for continual learning. Instead of viewing them as a new task for updating, we have to filter out such anomalies to reduce the disturbance of extremely high-entropy data for the progression of convergence. Secondly, fewer efforts have been put into research regarding the explainability of continual learning, which leads to a lack of transparency and credibility of the updated neural networks. Elaborated explanations about the process and result of continual learning can help experts in judgment and making decisions. Therefore, we propose the conceptual design of an explainability module with experts in the loop based on techniques, such as dimension reduction, visualization, and evaluation strategies. This work aims to overcome the mentioned challenges by sufficiently explaining and visualizing the identified anomalies and the updated neural network. With the help of this module, experts can be more confident in decision-making regarding anomaly filtering, dynamic adjustment of hyperparameters, data backup, etc.
A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning. Herde, Marek; Huseljic, Denis; Mitrovic, Jelena; Granitzer, Michael; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, S. 1–6. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Active learning (AL) techniques hardly cope with complex annotations tasks, where, for example, annotations might express relationships across data modalities. As a use case, we consider the task of automatically detecting and reporting multimodal, polarized web content (PWC). Samples of this content type emerge dynamically, covering a broad spectrum of topics. Thus, training machine learning systems for detecting PWC is challenging, particularly if it needs to be done with minimum annotation cost. In this article, we propose the concept of multimodal AL for complex annotations in the context of PWC detection and formulate the resulting challenges as questions for future research.
Rethinking business models as sociotechnical intersections in data-economy that should be designed participatively. Horn, Viktoria; Engert, Simon; Draude, Claude. In Mensch und Computer 2022 - Workshopband, K. Marky, U. Grünefeld, T. Kosch (Hrsg.). Gesellschaft für Informatik e.V., Bonn, 2022.
- [ DOI ]
- [ BibSonomy-Post ]
Bußgeldadressaten nach dem BSIG unter besonderer Berücksichtigung des Entwurfs der zweiten Richtlinie zur Netz- und Informationssicherheit. Hubert, T.; Schaller, T. In Daten, Plattformen und KI als Dreiklang unserer Zeit. Tagungsband DSRI-Herbstakademie 2022, C. Heinze (Hrsg.), S. 825–843. Edewecht, 2022.
- [ BibSonomy-Post ]
Barriers for SMEs in Adopting Crowdsourcing. Hupe, Anna; Bretschneider, Ulrich; Trostmann, Tim; Stubbemann, Lena. In 35th Bled eConference Digital Restructuring and Human (Re)action, S. 233–248. University of Maribor Press, Maribor, Slovenia, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Despite its undisputable benefits for firms, crowdsourcing is rarely applied in small and medium sized enterprises (SME), yet. Until today extant literature provides only an uncomplete picture of the barriers that hinder SMEs from adopting crowdsourcing. Because of these incomplete insights on this phenomenon there is a great deal of uncertainty on how to overcome these barriers all the more. In the scope of an interview series with 15 SMEs we explore a range of different barriers. The findings from our study do not only expand the so far incomplete body of knowledge but also provide practical references for SMEs to be aware of the barriers. This simplifies avoiding them and successfully adopting crowdsourcing.
How to Govern the Crowd? Governance Mechanisms in Crowd Work. Hupe, Anna; Bretschneider, Ulrich. In Pre-ICIS Workshop on the Changing Nature of Work (SIG 11th CNoW). Copenhagen, Denmark, 2022.
- [ URL ]
- [ BibSonomy-Post ]
Machine-learned Behaviour Models for a Distributed Behaviour Repository. Jahl, A.; Baraki, H.; Jakob, S.; Fax, M.; Geihs, K. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022), Bd. 1, S. 188–199. Scitepress, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Dynamically organised multi-agent systems that consist of heterogeneous participants require cooperation to fulfil complex tasks. Such tasks are commonly subdivided into subtasks that have to be executed by individual agents. The necessary teamwork demands coordination of the involved team members. In contrast to typical approaches like agent-centric and organisation-centric views, our solution is based on the task-centric view and thus contains active task components which select agents focusing on their Skills. It enables an encapsulated description of the task flow and its requirements including team cooperation, organisation, and location-independent allocation processes. Besides agent properties that represent syntactical and semantic information, agent behaviours are considered as well. The main contributions of this paper are hyperplane-based machine-learned Behaviour Models that are generated to capture the behaviour and consider the Behaviour Implementations as black boxes. These Behaviour Models are provided by a distributed behaviour repository that enables tasks to actively select fitting Behaviour Implementations. We evaluated our approach based on agents playing chessboard-like games autonomously.
Designing for Cultural Values: Towards a Theory-motivated Method for Culture-sensitive Adaptation of Information Systems. Janson, Andreas; Dickhaut, Ernestine; Söllner, Matthias. In Proceedings of the 55th Hawaii International Conference on System Sciences. Hawaii International Conference on System Sciences, 2022.
- [ BibSonomy-Post ]
Data Analytics for Effective Decision-Making in Crises - Identifying Relevant Data Analytics Competencies for Automotive Procurement Departments. Klee, Sven; Janson, Andreas. In International Conference on Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crises become the norm for organizations, as recent years have shown. Especially the automotive industry is still facing disruptive changes such as e-mobility, connected cars or autonomous driving. Disrupted supply chains, related production downtimes and associated financial losses are consequences. Procurement departments are the interface between internal and external stakeholders in supply chains, and therefore, the central authority for managing crises. In such situations, effective decision-making is essential. Positive effects of data analytics on decision-making were part of numerous research endeavors, as well as related data analytics competencies. We conducted semi-structured interviews with experienced experts about relevant data analytics competencies in procurement departments. We present an overview specifically for procurement departments and derive implications of these competencies on decision-making. As a result, we apply our findings to existing research from a theoretical perspective and support procurement leaders and their departments in facing current and future challenges from a practical perspective.
Critical Tools for Machine Learning: Working with Intersectional Critical Concepts in Machine Learning Systems Design. Klumbytė, Goda; Draude, Claude; Taylor, Alex S. In 2022 ACM Conference on Fairness, Accountability, and Transparency, von FAccT ’22, S. 1528–1541. Association for Computing Machinery, New York, NY, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This paper investigates how intersectional critical theoretical concepts from social sciences and humanities research can be worked with in machine learning systems design. It does so by presenting a case study of a series of speculative design workshops, conducted in 2021. These workshops drew on intersectional feminist methodologies to construct interdisciplinary interventions in the design of machine learning systems, towards more inclusive, accountable, and contextualized systems design. The concepts of “situating/situated knowledges”, "figuration", "diffraction", and “critical fabulation/speculation” were taken up as theoretical and methodological tools for concept-led design workshops. This paper presents the design framework of the workshops and highlights tensions and possibilities with regards to interdisciplinary machine learning systems design towards more inclusive, contextualized, and accountable systems. It discusses the role that critical theoretical concepts can play in a design process and shows how such concepts can work as methodological tools that nonetheless require an open-ended experimental space to function. It presents insights and discussion points regarding what it means to work with critical intersectional knowledge that is inextricably connected to its historical and socio-political roots, and how this reframes what it might mean to design fair and accountable systems.
Implications from Responsible Human-Robot Interaction with Anthropomorphic Service Robots for Design Science. Knof, Merlind; Heinisch, Judith S.; Kirchhoff, Jérôme; Rawal, Niyati; David, Klaus; Von Stryk, Oskar; Stock-Homburg, Ruth Maria. In Proceedings of the 55th Hawaii International Conference on System Sciences, S. 5827–5836. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Accelerated by the COVID-19 pandemic, anthropomorphic service robots are continuously penetrating various domains of our daily lives. With this development, the urge for an interdisciplinary approach to responsibly design human-robot interaction (HRI), with particular attention to human dignity, privacy, compliance, and transparency, increases. This paper contributes to design science, in developing a new artifact, i.e., an interdisciplinary framework for designing responsible HRI with anthropomorphic service robots, which covers the three design science research cycles. Furthermore, we propose a multi-method approach by applying this interdisciplinary framework. Thereby, our finding offer implications for designing HRI in a responsible manner.
A Stopping Criterion for Transductive Active Learning. Kottke, Daniel; Sandrock, Christoph; Krempl, Georg; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), S. 468–484. Springer, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
In transductive active learning, the goal is to determine the correct labels for an unlabeled, known dataset. Therefore, we can either ask an oracle to provide the right label at some cost or use the prediction of a classifier which we train on the labels acquired so far. In contrast, the commonly used (inductive) active learning aims to select instances for labeling out of the unlabeled set to create a generalized classifier, which will be deployed on unknown data. This article formally defines the transductive setting and shows that it requires new solutions. Additionally, we formalize the theoretically cost-optimal stopping point for the transductive scenario. Building upon the probabilistic active learning framework, we propose a new transductive selection strategy that includes a stopping criterion and show its superiority.
Datenintermediäre als Fairness-Akteure in der Datenökonomie. Kropf, Jonathan; Lamla, Jörn; Uhlmann, Markus. In Zu treuen Händen? Verbraucherdatenschutz und digitale Selbstbestimmung. Verbraucherzentrale NRW e.V., 2022.
- [ URL ]
- [ BibSonomy-Post ]
ICT-enabled job crafting: How Business Unit Developers use Low-code Development Platforms to craft jobs. Li, Mahei Manhai; Peters, Christoph; Poser, Mathis; Eilers, Karen; Elshan, Edona. In International Conference on Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recently, businesses are introducing low-code development platforms (LCDP) that enable employees with little to no development expertise to develop their own systems to improve their work. These so-called business unit developers (BUDs) possess necessary domain knowledge to understand how to use LCDPs to create useful (self-) services. Using job resource demand theory and the job crafting model, we conceptualize that BUDs use of LCDPs can be framed using the theoretical lens of job crafting. Job crafting stems from vocational psychology and provides well-researched positive consequences, such as wellbeing and meaningfulness. Thus, our research objective is to understand how BUDs can use LCDPs to job craft to gain access to positive job crafting consequences. We interviewed 17 experts across three organizations that employ an LDCP for chatbots. Our results suggest that job crafting is a suitable framework for understanding the effects of LCDP use.
Student Research Abstract: Continuous-Time Generative Graph Neural Network for Attributed Dynamic Graphs. Moallemy-Oureh, Alice. In ACM/SIGAPP Symposium on Applied Computing (SAC), S. 600–603. ACM, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
The history of neural networks dates back to the early 1940s and has not only evolved rapidly over time but they are now amongst one of the most popular and powerful machine learning techniques. In this area, graph representation learning (GRL) using graph neural networks (GNNs) has emerged during the early 90s and developed into an impactful approach for modeling graph-structured real-world data, such as social or biological networks. There are a variety of successful applications of GRL in computational neuroscience, chemistry, mathematics, and so on. While temporal changes (dynamics) play an essential role in many real-world applications, most of the literature on GNNs and GRL, deals with static graphs. Since the few GNN models on dynamic graphs only consider exceptional cases of dynamics (i.e., attribute-dynamic graphs in discrete-time representation or structure-dynamic graphs in continuous-time representation), we aim to present a novel GNN model that can handle attribute-dynamic graphs in continuous time. This model learns any kind of graph information embedding, performs node/edge attribute forecasts, and allows for attribute-dynamic graph generation in both discrete and continuous-time.
Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting. Nivarthi, Chandana Priya; Vogt, Stephan; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), S. 1530–1536. IEEE, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
Keynote: Studying Affect at the Cross-Road of Psychology and Computer Science. Ohly, Sandra. In 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), S. 377–377. 2022.
- [ DOI ]
- [ BibSonomy-Post ]
CITIZEN PARTICIPATION IN INCREASINGLY DIGITALIZED GOVERNMENTAL ENVIRONMENTS – A SYSTEMATIC LITERATURE REVIEW. Pristl, Ann-Catrin Cara; Billert, Matthias Simon. In European Conference on Information Systems (ECIS 2022), S. 1–19. Timișoara, Romania, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Citizen participation in increasingly digitalized governmental environments can introduce fruitful capabilities to encourage citizens to engage in municipal affairs and through this take actively part in fostering smart cities’ effectiveness. However, the practical exploitation of recent knowledge is still not sufficiently operationalized, whilst research in this field yields various approaches focusing on diverse emphases. Therefore, the necessity of systematically collecting and afterwards analysing the existing literature towards this topic is obvious. This paper depicts a proceeding to systematically review the available literature towards the relevant research units on citizen participation. Overall, 48 topic-based papers were identified out of leading journals and conference papers about information systems. The main findings of the relevant papers were assessed to a proposed analytical framework consisting of increasing participation stages and two distinct focus groups namely government and citizens. Accordingly, the covered recent focus areas of research are identified to reveal where state-of-the-art research falls short. Consequently, the imperative of emphasising investigation regarding concepts for ICT-enabled services focusing the empowerment of citizens arises as being our contribution for guiding future research, whilst governments can practically benefit from the composed framework by using it for classifying, planning and implementing proposed participation activities.
Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources. Rauch, Lukas; Huseljic, Denis; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, S. 27–42. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.
Towards an Employee-Centered Design for Human-AI Collaboration: How Work Design Theory Informs the Design of AI Systems. Reinhard, Philipp; Li, Mahei Manhai; Leimeister, Jan Marco. In Pre-ICIS Workshop on the Changing Nature of Work (SIG 11th CNoW). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
IT support is under growing pressure to ensure efficient, flexible, and scalable use of digital technologies (Kumbakara, 2008). As a result, technical support staff is affected by monotonous work and work overload (Schmidt et al., 2022). Our research aims to augment the precarious workplace of support agents with artificial intelligence (AI). To incorporate an employee-centered perspective a priori and ensure positive impacts, we propose a framework for combining work design theory (e.g. Demerouti et al., 2001) and design science theory (Peffers et al., 2007, Niehaves & Ortbach 2016). The advances in AI promise to leverage large potential in optimizing and enhancing service processes and workplaces (Huang & Rust, 2018, de Keyser, 2019). Introducing AI into service processes, imply effects on work characteristics (Larivière et al., 2017). By combining human and artificial intelligence we propose hybrid intelligence (Dellermann et al., 2019) as a suitable solution for mitigating the persistent issues of support workers and the possible negative impacts of AI. To a great extent, IS research emphasizes the implied impacts of AI use in workplaces (Verma & Singh 2022, Wang et al., 2020). As such, work design models are widely used to empirically evaluate the impacts of AI design (Sturm & Peters, 2020), but are rarely utilized to substantiate the design of AI-augmented work systems. Only Poser et al. (2022) and Zschech et al. (2021) recently applied such models. The goal of this paper is to overcome the lack of work design in design science research (DSR) for AI-based systems and to steer the development into desired socio-technological configurations. The here presented work is expected to answer : How can work design theory inform the design of AI-augmented workplaces? [RQ1] How should a hybrid intelligence system be designed to augment IT support agents’ workplaces by incorporating work design theory? [RQ2] To systematically design the integration of AI, we make use of the DSR paradigm (Peffers et al., 2007). We first interview support agents and utilize the organizing move theory of Pentland (1992) and the technical support work theory of Das (2003) to ensure relevance. Based on a review of the IS literature on work design theories, we then derive a preliminary theoretical framework (Paul & Benito, 2018) [RQ1]. The framework represents a kernel theory for the development of meta design requirements. Contributing to the second research question, we design and subsequently evaluate the augmentation based on work-related outcomes [RQ2].
Understanding the Necessary Conditions of Multi-Source Trust Transfer in Artificial Intelligence. Renner, Maximilian; Lins, Sebastian; Söllner, Matthias; Thiebes, Scott; Sunyaev, Ali. In Proceedings of the 55th Hawaii International Conference on System Sciences. Hawaii International Conference on System Sciences, 2022.
- [ Abstract ]
- [ BibSonomy-Post ]
Trust plays an increasingly important role, especially in new emerging AI-capable technologies. While different frameworks on establishing trustworthy AI were developed, extant research mostly neglects trust transfer mechanisms. We focus on multi-source trust transfer while taking a dual trust perspective including trust in provider and trust in technology. Our study falls in the context of autonomous vehicles as a target and AI and vehicles as sources. While conducting a survey with 432 participants, we applied necessary condition analysis to understand which sources are necessary for a multi-source trust transfer. Our results indicate that for trust in technology, AI and vehicle technology are necessary sources. In contrast, for trust in provider, only vehicle provider represents a necessary source. We contribute to research by providing a fresh perspective on trust in AI-capable technologies, applying a novel data analysis method to reveal necessary trust sources, and consider duality of trust in trust transfer.
The Specificity and Helpfulness of Peer-to-Peer Feedback in Higher Education. Rietsche, Roman; Caines, Andrew; Schramm, Cornelius; Pfütze, Dominik; Buttery, Paula. In Workshop on Innovative Use of NLP for Building Educational Applications (BEA), S. 107–117. Association for Computational Linguistics, Seattle, Washington, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
With the growth of online learning through MOOCs and other educational applications, it has become increasingly difficult for course providers to offer personalized feedback to students. Therefore asking students to provide feedback to each other has become one way to support learning. This peer-to-peer feedback has become increasingly important whether in MOOCs to provide feedback to thousands of students or in large-scale classes at universities. One of the challenges when allowing peer-to-peer feedback is that the feedback should be perceived as helpful, and an import factor determining helpfulness is how specific the feedback is. However, in classes including thousands of students, instructors do not have the resources to check the specificity of every piece of feedback between students. Therefore, we present an automatic classification model to measure sentence specificity in written feedback. The model was trained and tested on student feedback texts written in German where sentences have been labelled as general or specific. We find that we can automatically classify the sentences with an accuracy of 76.7% using a conventional feature-based approach, whereas transfer learning with BERT for German gives a classification accuracy of 81.1%. However, the feature-based approach comes with lower computational costs and preserves human interpretability of the coefficients. In addition we show that specificity of sentences in feedback texts has a weak positive correlation with perceptions of helpfulness. This indicates that specificity is one of the ingredients of good feedback, and invites further investigation.
A Corpus for Suggestion Mining of German Peer Feedback. Rietsche, Roman; Ritz, Eva; Janda, Julius; Pfütze, Dominik. In Language Resources and Evaluation Conference (LREC), S. 5539–5547. Marseille, France, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Peer feedback in online education becomes increasingly important to meet the demand for feedback in large scale classes, such as e.g. Massive Open Online Courses (MOOCs). However, students are often not experts in how to write helpful feedback to their fellow students. In this paper, we introduce a corpus compiled from university students’ peer feedback to be able to detect suggestions on how to improve the students’ work and therefore being able to capture peer feedback helpfulness. To the best of our knowledge, this corpus is the first student peer feedback corpus in German which additionally was labelled with a new annotation scheme. The corpus consists of more than 600 written feedback (about 7,500 sentences). The utilisation of the corpus is broadly ranged from Dependency Parsing to Sentiment Analysis to Suggestion Mining, etc. We applied the latter to empirically validate the utility of the new corpus. Suggestion Mining is the extraction of sentences that contain suggestions from unstructured text. In this paper, we present a new annotation scheme to label sentences for Suggestion Mining. Two independent annotators labelled the corpus and achieved an inter-annotator agreement of 0.71. With the help of an expert arbitrator a gold standard was created. An automatic classification using BERT achieved an accuracy of 75.3%.
Unleashing Process Mining for Education: Designing an IT-Tool for Students to Self-Monitor their Personal Learning Paths. Ritz, Eva; Wambsganss, Thiemo; Rietsche, Roman; Schmitt, Anuschka; Oeste-Reiß, Sarah; Leimeister, Jan Marco. In Internationale Tagung Wirtschaftsinformatik (WI). Nürnberg, Germany, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The ability of students to self-monitor their learning paths is in demand as never before due to the recent rise of online education formats, which entails less interaction with lecturers. Recent advantages in educational process mining (EPM) offer new opportunities to monitor students’ learning paths by processing log data captured by technology-mediated learning environments. However, current literature falls short on providing user-centered design principles for IT-tools which can monitor learning paths using EPM. Hence, in this paper, we examine how to design a self-monitoring tool that supports students to evaluate their learning paths. Based on theoretical insights of 66 papers and nine user interviews, we propose seven design principles for an IT-tool which facilitates self-monitoring for students based on EPM. Further, we evaluate the design principles with seven potential users. Our results demonstrate a promising approach to help students improve their self-efficacy in their individual learning process using EPM.
Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving. Rösch, Kevin; Heidecker, Florian; Truetsch, Julian; Kowol, Kamil; Schicktanz, Clemens; Bieshaar, Maarten; Sick, Bernhard; Stiller, Christoph. In IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI, S. 86–93. IEEE, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.
Requirements for an IT Support System based on Hybrid Intelligence. Schmidt, Simon L.; Li, Mahei Manhai; Peters, Christoph. In Hawaii International Conference on System Sciences (HICSS). 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In our digital world, all companies need IT support. The IT support staff is under high pressure solving user-based issues and facing an increase of heterogeneous systems. Hybrid intelligence could solve many issues due to the combination of machine power and the individual strengths of humans. As a part of a bigger design science research project, this paper derives requirements for an IT support system based on hybrid intelligence (ISSHI). 17 requirements from the literature and 21 requirements from 24 indepth interviews with IT support managers and support-agents from three different companies have been derived. These were evaluated and refined with a second interview series of five IT support stakeholders that led to a total of 24 consolidated requirements. Finally, these requirements were used to inform a system architecture for an ISSHI. This architecture shall serve as a foundation for future research directions regarding hybrid intelligence in IT support.
Examining Trust in Conversational Systems: Conceptual and Empirical Findings on User Trust, Related Behavior, and System Trustworthiness. Schmitt, Anuschka. In AAAI/ACM Conference on AI, Ethics, and Society (AIES). Oxford, United Kingdom, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Machine learning (ML)-based conversational systems represent a value enabler for human-machine interaction. Simultaneously, the opacity, complexity, and humanness accompanied by such systems introduce their own issues, including trust misalignment. While trust is viewed as a prerequisite for effective system use, few studies have considered calibrating for appropriate trust, and empirically testing the relationship between trust and related behavior. Moreover, the desired implications of transparency-enhancing design cues are ambiguous. My research aims to explore the impact of system performance on trust, the dichotomy between trust and behavior, and how transparency might help attenuate the effects caused by low system performance in the specific context of decision-making tasks assisted by ML-based conversational systems.
Conceptual Foundations on Debiasing for Machine Learning-Based Software. Schmitt, Anuschka; Walser, Maximilian; Fahse, Tobias Benjamin. In International Conference of Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Machine learning (ML)-based software’s deployment has raised serious concerns about its pervasive and harmful consequences for users, business, and society inflicted through bias. While approaches to address bias are increasingly recognized and developed, our understanding of debiasing remains nascent. Research has yet to provide a comprehensive coverage of this vast growing field, much of which is not embedded in theoretical understanding. Conceptualizing and structuring the nature, effect, and implementation of debiasing instruments could provide necessary guidance for practitioners investing in debiasing efforts. We develop a taxonomy that classifies debiasing instrument characteristics into seven key dimensions. We evaluate and refine our taxonomy through nine experts and apply our taxonomy to three actual debiasing instruments, drawing lessons for the design and choice of appropriate instruments. Bridging the gaps between our conceptual understanding of debiasing for ML-based software and its organizational implementation, we discuss contributions and future research.
Designing for Conversational System Trustworthiness: The Impact of Model Transparency on Trust and Task Performance. Schmitt, Anuschka; Wambsganss, Thiemo; Janson, Andreas. In European Conference on Information Systems (ECIS). Timișoara, Romania, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Designing for system trustworthiness promises to address challenges of opaqueness and uncertainty introduced through Machine Learning (ML)-based systems by allowing users to understand and interpret systems’ underlying working mechanisms. However, empirical exploration of trustworthiness measures and their effectiveness is scarce and inconclusive. We investigated how varying model confidence (70% versus 90%) and making confidence levels transparent to the user (explanatory statement versus no explanatory statement) may influence perceptions of trust and performance in an information retrieval task assisted by a conversational system. In a field experiment with 104 users, our findings indicate that neither model confidence nor transparency seem to impact trust in the conversational system. However, users’ task performance is positively influenced by both transparency and trust in the system. While this study considers the complex interplay of system trustworthiness, trust, and subsequent behavioral outcomes, our results call into question the relation between system trustworthiness and user trust.
A Practical Evaluation of Active Learning Approaches for Object Detection. Schneegans, Jan; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, S. 49–67. 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.
“I Will Follow You!” – How Recommendation Modality Impacts Processing Fluency and Purchase Intention. Schwede, Melanie; Zierau, Naim; Janson, Andreas; Hammerschmidt, Maik; Leimeister, Jan Marco. In International Conference on Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Although conversational agents (CA) are increasingly used for providing purchase recommendations, important design questions remain. Across two experiments we examine with a novel fluency mechanism how recommendation modality (speech vs. text) shapes recommendation evaluation (persuasiveness and risk), the intention to follow the recommendation, and how modality interacts with the style of recommendation explanation (verbal vs. numerical). Findings provide robust evidence that text-based CAs outperform speech-based CAs in terms of processing fluency and consumer responses. They show that numerical explanations increase processing fluency and purchase intention of both recommendation modalities. The results underline the importance of processing fluency for the decision to follow a recommendation and highlight that processing fluency can be actively shaped through design decisions in terms of implementing the right modality and aligning it with the optimal explanation style. For practice, we offer actionable implications on how to make effective sales agents out of CAs.
Examining the Antecedents of Creative Collaboration with an AI Teammate. Siemon, Dominik; Elshan, Edona; de Vreede, Triparna; Oeste-Reiß, Sarah; de Vreede, Gert Jan; Ebel, Philipp. In International Conference on Information Systems (ICIS). Copenhagen, Denmark, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
With the advent of artificial intelligence (AI), individuals are increasingly teaming up with AI-based systems to enhance their creative collaborative performance. When working with AI-based systems, several aspects of team dynamics need to be considered, which raises the question how humans’ approach and perceive their new teammates. In an experimental setting, we investigate the influence of social presence in a group ideation process with an AI-based teammate and examine its effects on the motivation to contribute. Our results show a multi-mediation model in which social presence indirectly influences whether human team members are motivated to contribute to a team with AI-based teammates, which is mediated by willingness to depend and team-oriented commitment.
Why Do We Turn to Virtual Companions? A Text Mining Analysis of Replika Reviews. Siemon, Dominik; Strohmann, Timo; Khosrawi-Rad, Bijan; de Vreede, Triparna; Elshan, Edona; Meyer, Michael. In Americas Conference on Information Systems (AMCIS). Minneapolis, Minnesota, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Many people globally experience the feeling of loneliness and struggle with its consequences. A modern way to deal with this loneliness and lack of companionship is to use empathetic and emotional conversational agents. Often referred to as virtual companions, these agents can engage in human-like conversations with their users and build relationships with them through modern artificial intelligence technologies. One established service of such virtual companions is Replika, which we investigate in this study to explore what users expect to gain from long-term interactions with virtual companions and what they tend to talk about with them. Using a text mining approach and 119,831 reviews of the Replika service, we analyze users' sentiments, emotions, and topics. Our results show that users interact with virtual companions to cope with their loneliness and, especially, to address their mental well-being. Furthermore, Replika users have a joyful and beneficial experience during long-term interaction with such virtual companions.
LG4AV: Combining Language Models and Graph Neural Networks for Author Verification. Stubbemann, Maximilian; Stumme, Gerd. In Advances in Intelligent Data Analysis XX, T. Bouadi, E. Fromont, E. Hüllermeier (Hrsg.), S. 315–326. Springer International Publishing, Cham, 2022.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The verification of document authorships is important in various settings. Researchers are for example judged and compared by the amount and impact of their publications and public figures are confronted by their posts on social media. Therefore, it is important that authorship information in frequently used data sets is correct. The question whether a given document is written by a given author is commonly referred to as authorship verification (AV). While AV is a widely investigated problem in general, only few works consider settings where the documents are short and written in a rather uniform style. This makes most approaches impractical for bibliometric data. Here, authorships of scientific publications have to be verified, often with just abstracts and titles available. To this point, we present LG4AV which combines language models and graph neural networks for authorship verification. By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style is, at least to some extent, standardized. By the incorporation of a graph neural network structure, our model can benefit from relations between authors that are meaningful with respect to the verification process.
Adaptive Empathy Learning Support in Peer Review Scenarios. Wambsganss, Thiemo; Söllner, Matthias; Koedinger, Kenneth; Leimeister, Jan Marco. In ACM CHI Conference on Human Factors in Computing System (CHI). New Orleans, Louisiana, USA, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Advances in Natural Language Processing offer techniques to de- tect the empathy level in texts. To test if individual feedback on certain students’ empathy level in their peer review writing pro- cess will help them to write more empathic reviews, we developed ELEA, an adaptive writing support system that provides students with feedback on the cognitive and emotional empathy structures. We compared ELEA to a proven empathy support tool in a peer review setting with 119 students. We found students using ELEA wrote more empathic peer reviews with a higher level of emotional empathy compared to the control group. The high perceived skill learning, the technology acceptance, and the level of enjoyment provide promising results to use such an approach as a feedback application in traditional learning settings. Our results indicate that learning applications based on NLP are able to foster empathic writing skills of students in peer review scenarios.
Evaluation von Icons für LED-basierte Haltestellenanzeiger im öffentlichen Personennahverkehr. Wehr, F.; Schmidt, L. In Technologie und Bildung in hybriden Arbeitswelten: 68. Kongress der Gesellschaft für Arbeitswissenschaft (Magdeburg 2022), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.8.9). GfA-Press, Sankt Augustin, 2022.
- [ Abstract ]
- [ BibSonomy-Post ]
In der hier vorgestellten Laborstudie wurde die Interpretierbarkeit von Fahrgastinformationen zur Belegung von Mehrzweckflächen (MZF) in einer Straßenbahn über einen realen LED-basierten Anzeiger und die Auswirkung dieser Fahrgastinformation auf das voraussichtliche Nutzungsverhalten untersucht. Dafür wurden im Within-Subject Design (N = 30) drei Darstellungsvarianten zur MZF-Belegung hinsichtlich Interpretationszeit, Fehlerfreiheit der Entscheidung und subjektiver Entscheidungssicherheit verglichen. Weiterhin wurde auf Basis des TAM-Modells die wahrgenommene Nützlichkeit erhoben. Die Ergebnisse zeigen keine signifikanten Unterschiede zwischen den Darstellungsvarianten. Die Fahrgastinformation zur Belegung von MZF wurde insgesamt als nützlich wahrgenommen.
A Holistic View on Probabilistic Trajectory Forecasting -- Case Study: Cyclist Intention Detection. Zernetsch, Stefan; Reichert, Hannes; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), S. 265–272. IEEE, 2022.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This article presents a holistic approach for probabilistic cyclist intention detection. By combining probabilities for the current cyclist motion states with a probabilistic ensemble trajectory forecast, we are able to generate reliable estimates of cyclists’ future positions. The probabilities are used as weights in the probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting). By weighting the specialized models, we create forecasts in the form of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a widely used unimodal approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. By comparing two different methods for basic movement detection, one based on the past cyclist trajectory and one using past image sequences, we demonstrate that the results can be further improved by incorporating video information. Our methods are evaluated using a dataset created at a public intersection. The code and the dataset are publicly available.

2021[ to top ]

Digital Shadows in Self-Improving System Integration: A Concept Using Generative Modelling. Al-Falouji, Ghassan; Gruhl, Christian; Tomforde, Sven. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 166–171. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
DELEN – A Process Model for the Systematic Development of Legitimate Digital Nudges. Barev, Torben Jan; Schöbel, Sofia; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Design Science Research in Information Systems and Technology (DESRIST), Bd. 12807, L. Chandra Kruse, S. Seidel, G. I. Hausvik (Hrsg.), S. 299–312. Springer, Cham, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Digital nudging is a promising approach from behavioral economics. In deci-sions where individuals tend to struggle, nudges can support users of digital systems by aligning their behavior with their preferences. Despite their wide use, most digital nudges are designed to support the intended behavior from the perspective of a company while neglecting potential legal, ethical, or individual constraints or preferences. With modern technologies such as artificial intelli-gence or big data, these issues multiply and with the increasing effectiveness of digital nudges and use of new technologies, this has become even more critical. Thus, in this paper we follow a Design Science Research approach to develop a process model for the systematic development of legitimate nudges (DELEN). Legitimacy requires that dealings between different entities shall be fair. Unlike other models, we set normative boundaries derived from literature, expert in-terviews, and target group segmentation as integral elements. Target group seg-mentation increases nudge effectiveness and avoids unnecessary burdens for other individuals. By doing so, the DELEN process model paves the way for legitimate and effective digital nudges.
The Dark Side of Privacy Nudging – An Experimental Study in the Context of a Digital Work Environment. Barev, Torben Jan; Schwede, Melanie; Janson, Andreas. In Hawaii International Conference on System Sciences (HICSS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Privacy nudging is a promising method to get users to disclose less personal information in digital work environments. In this work, we tested two digital privacy nudges: a social and a framing nudge. To empirically measure the effectiveness of the two privacy nudges, we developed an online experiment. We evaluated 223 data sets with the partial least squares structural equation modeling (PLS-SEM) and a two-factorial Analysis of Variance (ANOVA). The results indicate that privacy nudges negatively influence information disclosure behavior. The privacy framing nudge has a direct and indirect effect, while the privacy social nudge has only an indirect effect on the information disclosure behavior. Individuals exposed to the privacy nudges perceived the stimulus as threat. Importantly, both nudges spark negative feelings. With this research, we are contributing to the discussion of what drives privacy nudge effectiveness and influences information disclosure behavior in digital work environments.
What do you mean? A Review on Recovery Strategies to Overcome Conversational Breakdowns of Conversational Agents. Benner, Dennis; Elshan, Edona; Schöbel, Sofia; Janson, Andreas. In International Conference on Information Systems (ICIS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Since the emergence of conversational agents, this technology has seen continuous development and research. Today, advanced conversational agents are virtually omnipresent in our everyday lives. Albeit the numerous improvements in their conversational capabilities, breakdowns are still a persistent issue. Such breakdowns can result in a very unpleasant experience for users and impair the future success of conversational agents. This issue has been acknowledged by many researchers recently. However, the research on strategies to overcome conversational breakdowns is still inconclusive, and further research is needed. Therefore, we conduct a systematic literature analysis to derive conceptual conversational breakdown recovery strategies from literature and highlight future research avenues to address potential gaps. Thus, we contribute to theory of human-agent interaction by deriving and assessing recovery strategies and suggesting leads for novel recovery strategies.
A Theory-Driven Design Science Research Agenda Towards Gamified Videos. Benner, Dennis; Schöbel, Sofia. In International Conference on Wirtschaftsinformatik (WI). Duisburg-Essen, Germany, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Digitalization has opened new opportunities but also brought new challenges such as lower engagement of students in online training. Especially learning videos need to be changed in their design and structure to make them more engaging for users. So far, overarching design principles are missing that support the development of gamified learning videos. In our research in progress paper we present an overarching approach on how to develop meaningful gamified learning videos. With our design science research approach, we plan to derive design principles and design features from our state-of-the-art design requirements. Additionally, we will conduct a field experiment to put our theoretical contributions to test and gather practical insights. Our research contributes to theory, by clarifying how and why gamified videos can support better learning. In a long run, practical contributions can be given to developers about how to construct gamified learning videos.
Exploring the State-of-the-Art of Persuasive Design for Smart Personal Assistants. Benner, Dennis; Schöbel, Sofia; Janson, Andreas. In International Conference on Wirtschaftsinformatik (WI). Duisburg-Essen, Germany, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Driven by technological advances, smart personal assistants (SPA) have gained importance in human-computer interaction. SPAs can influence user behavior and persuade them towards an outcome. However, users often lack motivated to interact with SPAs. One way to support this interaction is persuasive system design; considering concepts as gamification and/or digital nudging. Although SPA research has increased recently, there is still no shared knowledge about persuasive designs. Therefore, we aim to identify the current state-of-the-art for persuasive SPA design to understand how interactions and designs can be improved referring to persuasive system design. Thus, we conduct a systematic literature analysis to represent how gamification and digital nudging are used to design SPAs and conclude if and how those concepts can support SPA interactions. Consequently, we contribute to theory, providing better understanding about SPA interaction and design making SPAs more engaging and entertaining. Practitioners can use this contribution for persuasive SPA designs.
It is only for your own good, or is it? Ethical Considerations for Designing Ethically Conscious Persuasive Information Systems. Benner, Dennis; Schöbel, Sofia; Janson, Andreas. In Americas Conference on Information Systems (AMCIS). Association for Information Systems, Montreal, Kanada, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Persuasive designs, including gamification and digital nudging, have become well renowned during the last years and have been implemented successfully across different sectors including education, e-health, e-governance, e-finance and general information systems. In this regard, persuasive design can support desirable changes in attitude and behavior of users in order to achieve their own goals. However, such persuasive influence on individuals raises ethical questions as persuasive designs can impair the autonomy of users or persuade the user towards goals of a third party and hence lead to unethical decision-making processes. In human-computer interaction this is especially significant with the advent of advanced artificial intelligence that can emulate human behavior and thus bring new dynamics into play. Therefore, we conduct a systematic literature analysis with the goal to compile an overview of ethical considerations for persuasive system design, derive potential guidelines for ethical persuasive designs and shed light on potential research gaps.
Cyclist Motion State Forecasting -- Going beyond Detection. Bieshaar, M.; Zernetsch, S.; Riepe, K.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, Orlando, FL, USA, 2021.
- [ BibSonomy-Post ]
A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving. Bieshaar, Maarten; Herde, Marek; Huselijc, Denis; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. 2021.
- [ BibSonomy-Post ]
Description of Corner Cases in Automated Driving: Goals and Challenges. Bogdoll, Daniel; Breitenstein, Jasmin; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard; Fingscheidt, Tim; Zöllner, J. Marius. In Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV, S. 1023–1028. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands. Botache, Diego; Bethke, Florian; Hardieck, Martin; Bieshaar, Maarten; Brabetz, Ludwig; Ayeb, Mohamed; Zipf, Peter; Sick, Bernhard. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS), S. 120–130. IEEE, Washington, DC, USA, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Exploring the Impact of Crowd Members’ Motivation on Idea Quality in Online Innovation Communities. Bretschneider, Ulrich. In Annual Meeting of the Academy of Management (AOM). 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Since many years, several firms host Virtual Idea Communities (VIC), in which the crowd focuses on voluntarily developing ideas for new product development (NPD). Both, scholars and practitioners share a strong interest in understanding the factors that enhance crowd members’ individual ideation outcome, meaning the quality of ideas, since the value of user ideas is not only essential for the survival of a VIC, but it also directly affects the innovation effects of firm’s NPD. Although there exist first insights on what influences idea quality, empirical studies that provide evidence of which forms of crowd members motivations are positively linked to higher ideation outcome are neglected. In this research, we build a theoretical model explaining which motives of crowd members for engaging in ideation have a positive impact on the quality of ideas they developed. To test our theory, we employed empirical data from users of the VIC by the software manufacturer SAP. For the first time, we found that crowd members of VIC are motivated to send capability signals through their ideas and thus be more creative. Further, crowd members with higher levels of fun and learning motivation produce ideas of higher quality, whereas this association depends on their level of flow experience. Our empirical results provide important contributions to IS research and practice. On the basis of our findings it is possible to design socio-technical artefacts for VICs that stimulate users’ capability-, fun- and learning motives and in turn will lead to ideas of higher quality.
“All Names Are Pseudonyms”: A Critical Reflection on Pseudonymizing Names in HCI: “All Names Are Pseudonyms”. Dankwa, Nana Kesewaa. In CHI EA ’21: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, S. 1–6. Association for Computing Machinery, New York, NY, USA, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
A person's name embodies identity. During user studies in Human Computer Interaction (HCI), persons are often renamed (pseudonymization) to hide their identity for privacy and ethical reasons. Pseudonymization occurs mostly as a “silent” affair of due diligence. Researchers barely give substantial information to the process nor reveal a reflexive position nor acknowledge the underlying elements of power and identity negotiation. As HCI advances in mitigating the design of biased technologies and breaking oppressive structures, I argue, in this paper, the need for the field to re-consider research requirements such as pseudonymization as possible to embody oppressive structures and erase identity. I present a review of papers from the 2020 CHI Conference on Human Factors in Computing Systems (CHI ‘20) that illustrate how silent the HCI approach is. My argument is built on Critical Race Theory, questioning the objectivity of such technical requirements. I use personal narratives to bolster this argument, ending with a call to the HCI community to acknowledge the power and privilege in renaming participants with three recommendations for consideration.
Setting Diversity at the Core of HCI. Dankwa, Nana Kesewaa; Draude, Claude. In Universal Access in Human-Computer Interaction. Design Methods and User Experience, Bd. 12768 von Lecture Notes in Computer Science, M. Antona, C. Stephanidis (Hrsg.), S. 39–52. Springer International Publishing, Cham, 2021.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
The advancing awareness of diversity in HCI is touted as laudable in addressing inequality and the digital divide. This progress however has not been reflected in HCI research. Diversity in HCI has focused on giving underrepresented users voice and confronting homogeneity. By increasing representations, though a diversity affinity is immediately visible, the deconstruction of institutionalized prejudice fails. Additionally, underrepresented voices have the unsurmountable task of representing their group. These approaches to diversity become tokenistic fixes failing to tackle the systemic causes of inequality.
LEGIT Methodology: Towards Capturing Legal Compatibility of Design Science Artifacts. Dickhaut, Ernestine; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Design Science Research in Information Systems and Technology (DESRIST), Bd. 12807, L. Chandra Kruse, S. Seidel, G. I. Hausvik (Hrsg.), S. 293–298. Lecture Notes in Computer Science (Spring Cham), Kristiansand, Norway, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Higher legal standards with regards to the data protection of individu-als such as the General Data Protection Regulation (GDPR) are increasing the pressure on developers of IT artifacts. Typically, when developing systems, we subsequently evaluate them with users to elaborate aspects such as user experi-ence perceptions. However, nowadays, other evaluation aspects such as legality and data policy issues are also important criteria for system development. For this purpose, we introduce LEGIT (legal design science evaluation), which pro-vides developers with guidance when considering legal requirements. We use the case of the GDPR to illustrate the feasibility, applicability, and benefit to the de-velopment process. With this novel method adapted from law research, we are able to derive actionable guidance for developers to evaluate developer efforts in increasing legal compatibility. To illustrate our methodological approach, in this paper, we describe the key steps of the method with respect to the evaluation of a learning assistant. We develop an AI-based learning assistant for university stu-dents to demonstrate the application of the novel evaluation method. We briefly discuss how this procedure can serve as the foundation for a new evaluation method of legally compatible systems in design science research.
The Hidden Value of Patterns – Using Design Patterns to Whitebox Technology Development in Legal Assessments. Dickhaut, Ernestine; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Wirtschaftsinformatik (WI), von The Hidden Value of Patterns – Using Design Patterns to Whitebox Technology Development in Legal Assessments. University of Duisburg-Essen, Germany, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Higher legal standards with regards to data protection of individuals such as the European General Data Protection Regulation (GDPR) increase the pressure on developing lawful technologies. The development requires feedback from stakeholders such as legal experts that lack technical knowledge but are required to understand IT artifacts. As a solution, patterns can support interdisciplinary system development. We demonstrate how interdisciplinary patterns can support legal experts in arguing about technologies in court by introducing a law simulation study which is a well-known evaluation method in law. Our results show that patterns support legal experts in their argumentation about technologies in court. We provide theoretical contributions concerning cognitive fit theory about how patterns act as a bridge between the internal and external representation of problems and improve problem-solving performance related to the legal assessment of technology. In addition, we provide practical guidance for codifying and communicating design knowledge through patterns.
Developing Lawful Technologies – A Revelatory Case Study on Design Patterns. Dickhaut, Ernestine; Li, Mahei Manhai; Janson, Andreas; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Higher legal standards regarding the data protection of individuals, such as the European General Data Protection Regulation, increase the pressure on developing lawful systems. In the development of technologies, not only developers are involved. It also requires knowledge from other stakeholders, such as legal experts, that lack technical knowledge but are required to understand IT artifacts. We see two strings that can benefit from the use of design patterns: first, the well-known use of design patterns to support developers in case of recurring problems. Second, we see potential that legal experts, who have to interact with and understand complicated, novel technologies, benefit from the same patterns. We conduct a revelatory case study using design patterns to develop and assess a smart learning assistant. We scaffolded the case interpretation through the human-centered view of socio-materiality and provide contributions concerning the use of design patterns in the development and assessment of lawful technologies.
AI - Based On The Fly Design of Experiments in Physics and Engineering. Dingel, Kristina; Liehr, Alexander; Vogel, Michael; Degener, Sebastian; Meier, David; Niendorf, Thomas; Ehresmann, Arno; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 150–153. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Attribute Selection Using Contranominal Scales. Dürrschnabel, Dominik; Koyda, Maren; Stumme, Gerd. In Graph-Based Representation and Reasoning, T. Braun, M. Gehrke, T. Hanika, N. Hernandez (Hrsg.), S. 127–141. Springer International Publishing, Cham, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Formal Concept Analysis (FCA) allows to analyze binary data by deriving concepts and ordering them in lattices. One of the main goals of FCA is to enable humans to comprehend the information that is encapsulated in the data; however, the large size of concept lattices is a limiting factor for the feasibility of understanding the underlying structural properties. The size of such a lattice depends on the number of subcontexts in the corresponding formal context that are isomorphic to a contranominal scale of high dimension. In this work, we propose the algorithm ContraFinder that enables the computation of all contranominal scales of a given formal context. Leveraging this algorithm, we introduce {\$$}{\$$}{backslashdelta {\$$}{\$$}$$\delta$$-adjusting, a novel approach in order to decrease the number of contranominal scales in a formal context by the selection of an appropriate attribute subset. We demonstrate that {\$$}{\$$}{backslashdelta {\$$}{\$$}$$\delta$$-adjusting a context reduces the size of the hereby emerging sub-semilattice and that the implication set is restricted to meaningful implications. This is evaluated with respect to its associated knowledge by means of a classification task. Hence, our proposed technique strongly improves understandability while preserving important conceptual structures.
Force-Directed Layout of Order Diagrams Using Dimensional Reduction. Dürrschnabel, Dominik; Stumme, Gerd. In Formal Concept Analysis, A. Braud, A. Buzmakov, T. Hanika, F. Le Ber (Hrsg.), S. 224–240. Springer International Publishing, Cham, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Order diagrams allow human analysts to understand and analyze structural properties of ordered data. While an expert can create easily readable order diagrams, the automatic generation of those remains a hard task. In this work, we adapt force-directed approaches, which are known to generate aesthetically-pleasing drawings of graphs, to the realm of order diagrams. Our algorithm ReDraw thereby embeds the order in a high dimension and then iteratively reduces the dimension until a two-dimensional drawing is achieved. To improve aesthetics, this reduction is equipped with two force-directed steps where one step optimizes the distances of nodes and the other one the distances of lines in order to satisfy a set of a priori fixed conditions. By respecting an invariant about the vertical position of the elements in each step of our algorithm we ensure that the resulting drawings satisfy all necessary properties of order diagrams. Finally, we present the results of a user study to demonstrate that our algorithm outperforms comparable approaches on drawings of lattices with a high degree of distributivity.
Sense of Control for Empowerment in Hybrid Intelligence Service Systems. Eilers, Karen; Li, Mahei. In International Conference on Information Systems (ICIS). Workshop: Service and Information Systems Research for a Better Future. Austin, Texas, USA, 2021.
- [ BibSonomy-Post ]
Why the Agile Mindset Matters. Eilers, Karen; Simmert, Benedikt; Peters, Christoph; Leimeister, Jan Marco. In Academy of Management Annual Meeting (AOM). 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Volatility, uncertainty, ambiguity, and complexity (VUCA) are drivers in today’s business world. Therefore, an increasing number of organizations implement agility (agile methods) to cope with the rapid and accelerating change. However, these agile transformations do not succeed unhindered, and some fail. One reason for that is the employees lacking an agile mindset and they do not support or participate in the transformation. So far, knowledge of the agile mindset is in its infancy. A conceptualization for developing a measuring instrument on the individual level is lacking. Furthermore, the relevance of the agile mindset regarding organizational performance in a VUCA world is still unclear. Our study aims to close this gap. To do so, we examine the agile mindset with 15 qualitative interviews and conduct an online survey (N=449) to predict organizational agility and organizational performance based on the agile mindset. As for results, we conceptualize the agile mindset as an attitude that comprises four dimensions: ’learning spirit’, ‘collaborative exchange’, ‘empowered self-guiding’, and ‘iterative value creation’. We have found an indirect effect of the agile mindset affecting organizational performance towards organizational agility. These findings contribute to the agility and management research by providing both a conceptualization and a measuring instrument for the agile mindset. Furthermore, the agile mindset´s relevance in agile transformation is explained and its relation to organizational performance outlined. For successful agile transformation, executives must focus on the agile mindset of their employees and foster this by e.g. being a role model.
Opening the Black Box of Music Royalties with the Help of Hybrid Intelligence. Elshan, Edona; Engel, Christian; Ebel, Philipp. In Hawaii International Conference on System Sciences (HICCS). 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
The ever-increasing complexity of the music industry and the intensified resentment of artists towards collecting societies call for a transformation and a change of behavior within the music ecosystem. This article introduces a hybrid intelligence system, that ameliorates the current situation by combining the intelligence of humans and machines. This study proposes design requirements for hybrid intelligence systems in the music industry. Using a design science research approach, we identify design requirements both inductively from expert interviews and deductively from theory and present a first prototypical instantiation of a respective hybrid intelligence system. Overall, this shall enrich the body of knowledge of hybrid intelligence research by transferring its concepts into a new context. Furthermore, the identified design requirements shall serve as a foundation for researchers and practitioners to further explore and design hybrid intelligence in the music industry and beyond.
The Effect of Explanations on Trust in an Assistance System for Public Transport Users and the Role of the Propensity to Trust. Faulhaber, A. K.; Ni, I.; Schmidt, L. In Mensch und Computer 2021 - Tagungsband (Ingolstadt 2021), S. Schneegass, B. Pfleging, D. Kern (Hrsg.), S. 303–310. ACM, New York, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The present study aimed to investigate whether explanations increase trust in an assistance system. Moreover, we wanted to take the role of the individual propensity to trust in technology into account. We conducted an empirical study in a virtual reality environment where 40 participants interacted with a specific assistance system for public transport users. The study was in a 2x2 mixed design with the within-subject factor assistance system feature (trip planner and connection request) and the between-subject factor explanation (with or without). We measured trust as explicit trust via a questionnaire and as implicit trust via an operationalization of the participants’ behavior. The results showed that trust propensity predicted explicit trust, and explanations increased explicit trust significantly. This was not the case for implicit trust, though, suggesting that explicit and implicit trust do not necessarily coincide. In conclusion, our results complement the literature on explainable artificial intelligence and trust in automation and provide topics for future research regarding the effect of explanations on trust in assistance systems or other technologies.
Perception of Peripheral Visual Cues in Augmented Reality During Walking: A Pilot Study. Faulhaber, A. K.; Schmidt, L. In Arbeit HUMAINE gestalten: 67. Kongress der Gesellschaft für Arbeitswissenschaft (Bochum 2021), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.5.6). GfA-Press, Dortmund, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Augmented Reality (AR) glasses may be used in diverse mobile and multitasking contexts, for example, while walking. In such contexts, it is particularly important to display information without obscuring essential areas of central vision. Information can, thus, be presented to the peripheral vision. The objective of the present study was to investigate how peripheral visual cues should be displayed in AR to achieve efficient perception during walking. We conducted a pilot study and tested three different versions of directional cues presented while walking or standing still: simply popping up, moving towards the indicated direction, or changing color. The results indicated that the perception of peripheral cues in AR is generally less efficient while walking than standing still. Within the walking condition, the color-changing cue was perceived best.
Triadic Exploration and Exploration with Multiple Experts. Felde, Maximilian; Stumme, Gerd. In Formal Concept Analysis, A. Braud, A. Buzmakov, T. Hanika, F. Le Ber (Hrsg.), S. 175–191. Springer International Publishing, Cham, 2021.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Formal Concept Analysis (FCA) provides a method called attribute exploration which helps a domain expert discover structural dependencies in knowledge domains that can be represented by a formal context (a cross table of objects and attributes). Triadic Concept Analysis is an extension of FCA that incorporates the notion of conditions. Many extensions and variants of attribute exploration have been studied but only few attempts at incorporating multiple experts have been made. In this paper we present triadic exploration based on Triadic Concept Analysis to explore conditional attribute implications in a triadic domain. We then adapt this approach to formulate attribute exploration with multiple experts that have different views on a domain.
Vergleichende Evaluation von Augmented-Reality-Anwendungen zur Ergänzung von Lehrbüchern in der Berufsausbildung. Funk, J.; Schmidt, L. In Arbeit HUMAINE gestalten: 67. Kongress der Gesellschaft für Arbeitswissenschaft (Bochum 2021), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.2.1). GfA-Press, Dortmund, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
In der hier vorgestellten Laborstudie wurden zwei Arten markerbasierter Augmented-Reality-Ergänzungen zu einem Lehrbuch mit einer konventionellen Ergänzung in Papierform verglichen. Hierbei wurden drei Unterthemen aus der Ausbildung zum Kraftfahrzeugmechatroniker ausbalanciert um je eine Art der Zusatzinformation ergänzt. Dabei wurde der Lernerfolg mit Multiple-Choice-Aufgaben kontrolliert sowie die Gebrauchstauglichkeit (SUS), die Beanspruchung (NASA-rTLX), die räumliche Vorstellung (RV) und das Nutzererlebnis (UEQ) mit Fragebögen im Within-Subject Design (N = 24) erhoben. Die Ergebnisse zeigen ein höheres Nutzererlebnis und eine bessere räumliche Vorstellung bei Verwendung der AR im Vergleich zur konventionellen Ergänzung bei jeweils vergleichbarer niedriger Beanspruchung, hoher Gebrauchstauglichkeit sowie Lernleistung.
Kommentierung von § 24 (Datenverarbeitung zu wissenschaftlichen oder historischen Forschungszwecken und zu statistischen Zwecken), § 28a (Datenverarbeitung bei öffentlichen Auszeichnungen und Ehrungen), § 28b (Datenverarbeitung in Gnadenverfahren) und §§ 80 bis 89 (Informationsfreiheit) HDSIG. Geminn, Christian. In Hessisches Datenschutz- und Informationsfreiheitsgesetz, A. Roßnagel (Hrsg.). Nomos, Baden-Baden, 2021.
- [ BibSonomy-Post ]
Kommentierung von Art. 24 (Videoüberwachung) und 27 (Staatliche und kommunale Auszeichnungen und Ehrungen) BayDSG. Geminn, Christian. In Bayerisches Datenschutzgesetz, M. Schröder (Hrsg.). Nomos, Baden-Baden, 2021.
- [ BibSonomy-Post ]
Kommentierung von § 45 (Datenverarbeitung zu wissenschaftlichen oder historischen Forschungszwecken, archivarischen oder statistischen Zwecken) HDSIG. Geminn, Christian; Johannes, P. In Hessisches Datenschutz- und Informationsfreiheitsgesetz, A. Roßnagel (Hrsg.). Nomos, Baden-Baden, 2021.
- [ BibSonomy-Post ]
Alexa, are you still there? Understanding the Habitual Use of AI-Based Voice Assistants. Grünenfelder, Janay Ilya; Zierau, Naim; Janson, Andreas. In International Conference on Information Systems (ICIS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Voice assistants are a novel class of information systems that fundamentally change human–computer interaction. Although these assistants are widespread, the utilization of these information systems is oftentimes only considered on a surface level by individuals. In addition, prior research has focused predominantly on initial use instead of looking deeper into post-adoption and habit formation. In consequence, this paper reviews how the notion of habit has been conceptualized in relation to biographical utilization of voice assistants and presents findings based on a qualitative study approach. From a perspective of post-adoption users, the study suggests that existing habits persist, and new habits hardly ever form in the context of voice assistant utilization. This paper outlines four key factors that help explain voice assistant utilization behavior and furthermore provides practical implications that help to ensure continued voice assistant use in the future.
The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models. Gruhl, Christian; Hannan, Abdul; Huang, Zhixin; Nivarthi, Chandana; Vogt, Stephan. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 204–209. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
OHODIN -- Online Anomaly Detection for Data Streams. Gruhl, Christian; Tomforde, Sven. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 193–197. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning. Haase-Schütz, Christian; Stal, Rainer; Hertlein, Heinz; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), S. 9483–9490. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Exploring Scale-Measures of Data Sets. Hanika, Tom; Hirth, Johannes. In Formal Concept Analysis - 16th International Conference, ICFCA 2021, Strasbourg, France, June 29 - July 2, 2021, Proceedings, Bd. 12733 von Lecture Notes in Computer Science, A. Braud, A. Buzmakov, T. Hanika, F. L. Ber (Hrsg.), S. 261–269. Springer, 2021.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Quantifying the Conceptual Error in Dimensionality Reduction. Hanika, Tom; Hirth, Johannes. In Graph-Based Representation and Reasoning - 26th International Conference on Conceptual Structures, ICCS 2021, Virtual Event, September 20-22, 2021, Proceedings, Bd. 12879 von Lecture Notes in Computer Science, T. Braun, M. Gehrke, T. Hanika, N. Hernandez (Hrsg.), S. 105–118. Springer, 2021.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Anomaly based Resilient Network Intrusion Detection using Inferential Autoencoders. Hannan, Abdul; Gruhl, Christian; Sick, Bernhard. In IEEE International Conference on Cyber Security and Resilience (CSR), S. 1–7. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving. Heidecker, Florian; Breitenstein, Jasmin; Rösch, Kevin; Löhdefink, Jonas; Bieshaar, Maarten; Stiller, Christoph; Fingscheidt, Tim; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), S. 644–651. IEEE, Nagoya, Japan, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Novelty based Driver Identification on RR Intervals from ECG Data. Heidecker, Florian; Gruhl, Christian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, S. 407–421. IEEE, Milan, Italy, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks. Heidecker, Florian; Hannan, Abdul; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, S. 361–374. IEEE, Milan, Italy, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Multi-annotator Probabilistic Active Learning. Herde, Marek; Kottke, Daniel; Huseljic, Denis; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), S. 10281–10288. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Smart Infrastructure: A Research Junction. Hetzel, Manuel; Reichert, Hannes; Doll, Konrad; Sick, Bernhard. In IEEE International Smart Cities Conference (ISC2). IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Uncertainty and Utility Sampling with Pre-Clustering. Huang, Zhixin; He, Yujiang; Vogt, Stephan; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. 2021.
- [ BibSonomy-Post ]
Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks. Huseljic, Denis; Sick, Bernhard; Herde, Marek; Kottke, Daniel. In International Conference on Pattern Recognition (ICPR), S. 9172–9179. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Blockchain-based Task-centric Team Building. Jahl, Alexander; Jakob, Stefan; Baraki, Harun; Alhamwy, Yasin; Geihs, Kurt. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence. SciTePress, 2021.
- [ BibSonomy-Post ]
Adaptive Semantic Routing in Dynamic Environments. Jakob, Stefan; Baraki, Harun; Jahl, Alexander; Chiadjeu, Eric Douglas Nyakam; Alhamwy, Yasin; Geihs, Kurt. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence. SciTePress, 2021.
- [ BibSonomy-Post ]
Generating Commonsense Ontologies with Answer Set Programming. Jakob, Stefan; Jahl, Alexander; Baraki, Harun; Geihs, Kurt. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence. SciTePress, 2021.
- [ BibSonomy-Post ]
Critical Tools for Machine Learning: Situating, Figuring, Diffracting, Fabulating Machine Learning Systems Design. Klumbyte, Goda; Draude, Claude; Taylor, Alex. In CHItaly 2021: 14th Biannual Conference of the Italian SIGCHI Chapter, von CHItaly ’21. Association for Computing Machinery, Bolzano, Italy, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This workshop draws on feminist and other critical methodologies to construct interdisciplinary interventions in the design of machine learning systems. Theoretical concepts of “figuration”, “situating/situated knowledge”, “critical fabulation/speculation,” and “diffraction” are explored through hands-on experimentation to imagine and design machine learning systems in a more situated, inclusive, contextualize and accountable way. Through this “theory turned practice” approach the workshop aims to address systemic socio-cultural biases and develop more socially responsible frameworks of design. The workshop provides space for building a network for future research on interdisciplinary machine learning systems design.
Traffic Safety in Future Cities by Using a Safety Approach Based on AI and Wireless Communications. König, I.; Bachmann, M.; Bieshaar, M.; Schindler, S.; Lambrecht, F.; David, K.; Sick, B.; Hornung, G.; Sommer, C. In ITG-Symposium on Mobile Communication - Technologies and Applications, S. 1–6. Osnabrück, Germany, 2021.
- [ BibSonomy-Post ]
Statistical Analysis of Pairwise Connectivity. Krempl, Georg; Kottke, Daniel; Pham, Tuan. In International Conference on Discovery Science (DS), von Lecture Notes in Computer Science, S. 138–148. Springer, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks. Kress, Viktor; Zernetsch, Stefan; Doll, Konrad; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, S. 57–71. Springer, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders. Möller, Felix; Botache, Diego; Huseljic, Denis; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR, S. 1–10. 2021.
- [ URL ]
- [ BibSonomy-Post ]
Digitales Lernen – Datenschutzrechtliche Rechtsgrundlagen von Lernplattformen für Kinder und Erwachsene. Nebel, Maxi. In Aufwachsen in überwachten Umgebungen, Interdisziplinäre Positionen zu Privatheit und Datenschutz in Kindheit und Jugend, I. Stapf, R. Ammicht Quinn, M. Friedewald, J. Heesen, N. Krämer (Hrsg.). Nomos, 2021.
- [ BibSonomy-Post ]
Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems. Reichert, Hannes; Lang, Lukas; Rösch, Kevin; Bogdoll, Daniel; Doll, Konrad; Sick, Bernhard; Reuss, Hans-Christian; Stiller, Christoph; Zöllner, J. Marius. In IEEE International Smart Cities Conference (ISC2), S. 1–4. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Achieving Trustworthy Artificial Intelligence: Multi-Source Trust Transfer in Artificial Intelligence-capable Technology. Renner, Maximilian; Lins, Sebastian; Söllner, Matthias; Thiebes, Scott; Sunyaev, Ali. In International Conference on Information Systems (ICIS). 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Contemporary research focuses on examining trustworthy AI but neglects to consider trust transfer processes, proposing that users’ established trust in a familiar source (e.g., a technology or person) may transfer to a novel target. We argue that such trust transfer processes also occur in the case of novel AI-capable technologies, as they are the result of the convergence of AI with one or more base technologies. We develop a model with a focus on multi-source trust transfer while including the theoretical framework of trust duality (i.e., trust in providers and trust in technologies) to advance our understanding about trust transfer. A survey among 432 participants confirms that users transfer their trust from known technologies and providers (i.e., vehicle and AI technology) to AI-capable technologies and their providers. The study contributes by providing a novel theoretical perspective on establishing trustworthy AI by validating the importance of the duality of trust.
About the Ambiguity of Data Augmentation for 3D Object Detection in Autonomous Driving. Reuse, Matthias; Simon, Martin; Sick, Bernhard. In Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV, S. 979–987. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Artificial Intelligence in the Customer Journey: A Systematic Overview of the Most Popular Use Cases Through the Creation of AI Archetypes. Sander, Richard; Peters, Christoph. In Conference of the European Association for Research on Services (RESER). Heilbronn, Germany, 2021.
- [ URL ]
- [ BibSonomy-Post ]
Knowledge is Power: Provide your IT-Support with Domain-Specific High-Quality Solution Material. Schmidt, Simon L.; Li, Mahei Manhai; Weigel, Sascha; Peters, Christoph. In International Conference on Design Science Research in Information Systems and Technology (DESRIST). Springer, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
As more and more business processes are based on IT services the high availability of these processes is dependent on the IT-Support. Thus, making the IT-Support a critical success factor of companies. This paper presents how this department can be supported by providing the staff with domain-specific and high-quality solution material to help employees faster when errors occur. The solution material is based on previously solved tickets because these contain precise domain-specific solutions narrowed down to e.g., specific versions and configurations of hard-/software used in the company. To retrieve the solution material ontologies are used that contain the domain-specific vocabulary needed. Because not all previously solved tickets contain high-quality solution material that helps the staff to fix issues the designed IT-Support system separates lowfrom high-quality solution material. This paper presents (a) theory- and practicalmotivated design requirements that describe the need for automatically retrieved solution material, (b) develops two major design principles to retrieve domainspecific and high-quality solution material, and (c) evaluates the instantiations of them as a prototype with organic real-world data. The results show that previously solved tickets of a company can be pre-processed and retrieved to ITSupport staff based on their current queries.
Towards a Trust Reliance Paradox? Exploring the Gap Between Perceived Trust in and Reliance on Algorithmic Advice. Schmitt, Anuschka; Wambsganss, Thiemo; Söllner, Matthias; Janson, Andreas. In International Conference on Information Systems (ICIS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Beyond AI-based systems’ potential to augment decision-making, reduce organizational resources, and counter human biases, unintended consequences of such systems have been largely neglected so far. Researchers are undecided on whether erroneous advice acts as an impediment to system use or is blindly relied upon. As part of an experimental study, we turn towards the impact of incorrect system advice and how to design for failure-prone AI. In an experiment with 156 subjects we find that, although incorrect algorithmic advice is trusted less, users adapt their answers to a system’s incorrect recommendations. While transparency on a system’s accuracy levels fosters trust and reliance in the context of incorrect advice, an opposite effect is found for users exposed to correct advice. Our findings point towards a paradoxical gap between stated trust and actual behavior. Furthermore, transparency mechanisms should be deployed with caution as their effectiveness is intertwined with system performance.
Voice as a Contemporary Frontier of Interaction Design. Schmitt, Anuschka; Zierau, Naim; Janson, Andreas; Leimeister, Jan Marco. In European Conference on Information Systems (ECIS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Voice assistants’ increasingly nuanced and natural communication bears new opportunities for user experiences and task automation, while challenging existing patterns of human-computer interaction. A fragmented research field, as well as constant technological advancements, impede a common apprehension of prevalent design features of voice-based interfaces. As part of this study, 86 papers across domains are systematically identified and analysed to arrive at a common understanding of voice assistants. The review highlights perceptual differences to other human-computer interfaces and points out relevant auditory cues. Key findings regarding those cues’ impact on user perception and behaviour are discussed along with the three design strategies 1) personification, 2) individualization and 3) contextualization. Avenues for future research are lastly deducted. Our results provide relevant opportunities to researchers and designers alike to advance the design and deployment of voice assistants.
Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks. Schneegans, Jan; Bieshaar, Maarten; Heidecker, Florian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, S. 375–389. IEEE, Milan, Italy, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning -- A Case Study: Overtaking Cyclists. Schneegans, Jan; Eilbrecht, Jan; Zernetsch, Stefan; Bieshaar, Maarten; Doll, Konrad; Stursberg, Olaf; Sick, Bernhard. In Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV. 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
This work considers (deep) artiﬁcial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
Mithilfe von Privacy Nudging zu rechtsverträglichen Videokonferenztools. Schomberg, Sabrina; Dickhaut, Ernestine; Barev, Torben Jan; Janson, Andreas. In INFORMATIK 2021 – 51. Jahrestagung der Gesellschaft für Informatik, Bd. Computer Science & Sustainability, S. 979–994. Gesellschaft für Informatik e.V. (GI), Berlin, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die Covid-19 Pandemie hat zu enormen Veränderungen im Arbeitsalltag geführt. Videokonferenztools gewannen durch die Zusammenarbeit über Distanz an Bedeutung. In kürzester Zeit kamen in vielen Unternehmen Videokonferenztools verschiedener Hersteller zum Einsatz; der Datenschutz stand dabei in der Regel nicht an erster Stelle und es kam zu zahlreichen Datenschutzverstößen. Im Laufe der Pandemie rückte der Datenschutz mehr in den Fokus und es wurde nachgebessert. Wir wollen mit unserem Beitrag anregen Videokonferenztools nicht nur datenschutzkonform, sondern rechtsverträglich zu gestalten. Daher haben wir die Benutzeroberfläche eines Tools (Zoom) an den Stellen angepasst, an denen datenschutzsensibles Verhalten besonders kritisch ist. Wir zeigen, wie kleine Änderungen in der Benutzeroberfläche und die Integration von Privacy Nudges zu datenschutzsensiblem Verhalten führen können. Um diese sogenannten Privacy Nudges für Entwickelnde von Videokonferenztools so praktisch und zugänglich wie möglich zu machen, greifen wir auf das Konzept der Design Pattern aus der Systementwicklung zurück.
Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast. Schreiber, Jens; Vogt, Stephan; Sick, Bernhard. In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track, S. 118–134. Springer, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Technical & Data Protection Aspects of a Smart Digital Control Center for Smart Cities. Stroscher, Jan-Philipp; Schnaubelt, Marius; Sanchez Guinea, Alejandro; Fabian, Stefan; von Willich, Julius; Alhamwy, Yasin; Bauer, Maximilian; von Stryk, Oskar; Mühlhäuser, Max; Geihs, Kurt; Klingauf, Uwe; Hornung, Gerrit. In INFORMATIK 2021, G. für Informatik e.V. (GI) (Hrsg.), S. 1047–1058. Gesellschaft für Informatik, Bonn, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Female by Default? – Exploring the Effect of Voice Assistant Gender and Pitch on Trait and Trust Attribution. Tolmeijer, Suzanne; Zierau, Naim; Janson, Andreas; Wahdatehagh, Jalil; Leimeister, Jan Marco; Bernstein, Abraham. In Conference on Human Factors in Computing Systems (CHI). Yokohama, Japan, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Gendered voice based on pitch is a prevalent design element in many contemporary Voice Assistants (VAs) but has shown to strengthen harmful stereotypes. Interestingly, there is a dearth of research that systematically analyses user perceptions of different voice genders in VAs. This study investigates gender-stereotyping across two different tasks by analyzing the influence of pitch (low, high) and gender (women, men) on stereotypical trait ascription and trust formation in an exploratory online experiment with 234 participants. Additionally, we deploy a gender-ambiguous voice to compare against gendered voices. Our findings indicate that implicit stereotyping occurs for VAs. Moreover, we can show that there are no significant differences in trust formed towards a gender-ambiguous voice versus gendered voices, which highlights their potential for commercial usage.
ArgueBot: A Conversational Agent for Adaptive Argumentation Feedback. Wambsganss, Thiemo; Guggisberg, Sebastian; Söllner, Matthias. In 16th International Conference on Wirtschaftsinformatik (WI). 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
By combining recent advances in Natural Language Processing and Conversational Agent (CAs), we suggest a new form of human-computer interaction for individuals to receive formative feedback on their argumentation to help them to foster their logical reasoning skills. Hence, we introduce ArgueBot, a conversational agent, that provides adaptive feedback on students' logical argumentation. We, therefore, 1) leveraged a corpus of argumentative student-written peer-reviews in German, 2) trained, tuned, and benchmarked a model that identifies claims, premises and non-argumentative sections of a given text, and 3) built a conversational feedback tool. We evaluated ArgueBot in a proof-of-concept evaluation with students. The evaluation results regarding technology acceptance, the performance of our trained model, and the qualitative feedback indicate the potential of leveraging recent advances in Natural Language Processing for new human-computer interaction use cases for scalable educational feedback.
Towards the Design of a Student-Centered Question-Answering System in Educational Settings. Wambsganss, Thiemo; Haas, Leonie; Söllner, Matthias. In European Conference on Information Systems (ECIS) 2021. ECIS, 2021.
- [ Abstract ]
- [ BibSonomy-Post ]
Enrollments in distance-learning scenarios have been tremendously rising. Here, the ability of students to receive answers to questions is hindered due to an uneven educator-student ratio. Students often do not receive quick answers to simple questions, and educators feel stressed by answering the same questions repeatedly. However, advances in Natural-Language-Processing and Machine Learning bear the opportunity to design new forms of human-computer interaction by embedding question-answering (Q&A) models in conversational agents. Such a system enables students to receive personalized answers independent of an instructor, time, and location. This paper presents the first steps of our design science research project on designing a student-centered Q&A system that helps learners receive personalized answers in large-scale settings. Based on social response theory and user interviews, we propose five design principles for the design of a conversational Q&A system. Furthermore, we instantiate those principles as design features in a natively built prototype.
AI-based Argumentation Tutoring – A Novel System Class to Improve Learners’ Argumentation Skills. Wambsganss, Thiemo; Janson, Andreas; Söllner, Matthias; Leimeister, Jan Marco. In Annual Meeting of the Academy of Management (AOM). 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Argumentation is an omnipresent foundation of our daily communication and thinking. The ability to form convincing arguments is not only the fundament for persuading an audience of novel ideas but also plays a major role in strategic decision-making, negotiation, and productive civil discourse. However, students often struggle to develop argumentation skills due to a lack of individual and instant feedback in their learning journey, since providing feedback on the individual argumentation skills of learners is very time consuming and not scalable if conducted manually by educators. Following a design science research approach, we propose a new class of argumentation learning systems that provide students with individual and ongoing tutoring to support them in learning how to argue. We build our socio-technical design on a combination of user-centered design principles, a conceptualization of argumentation structures in student-written text, and Natural Language Processing and Machine Learning classifiers to provide individual feedback. To investigate if the new system class of AI-based argumentation tutoring systems helps students to improve their argumentation skills, we evaluated the novel artifact class in two empirical studies in comparison to traditional argumentation learning systems. In a laboratory experiment (study 1), as well as in a field experiment in a large-scale lecture over three months (study 2), we found that AI-based argumentation tutoring systems based on our design principles, argumentation schemes, and algorithms improve the short- and long-term argumentation skills of students significantly compared to the traditional argumentation learning approaches.
ArgueTutor: An Adaptive Dialog-Based Learning System for Argumentation Skills. Wambsganss, Thiemo; Küng, Tobias; Matthias, Söllner; Leimeister, Jan Marco. In ACM CHI Conference on Human Factors in Computing Systems (CHI). Yokohama, Japan, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Techniques from Natural-Language-Processing offer the opportunities to design new dialog-based forms of human-computer interaction as well as to analyze the argumentation quality of texts. This can be leveraged to provide students with adaptive tutoring when doing a persuasive writing exercise. To test if individual tutoring for students' argumentation will help them to write more convincing texts, we developed ArgueTutor, a conversational agent that tutors students with adaptive argumentation feedback in their learning journey. We compared ArgueTutor with 55 students to a traditional writing tool. We found students using ArgueTutor wrote more convincing texts with a better quality of argumentation compared to the ones using the alternative approach. The measured level of enjoyment and ease of use provides promising results to use our tool in traditional learning settings. Our results indicate that dialog-based learning applications combined with NLP text feedback have a beneficial use to foster better writing skills of students.
Supporting Cognitive and Emotional Empathic Writing of Students. Wambsganss, Thiemo; Niklaus, Christina; Söllner, Matthias; Handschuh, Siegfried; Leimeister, Jan Marco. In Joint Conference of the Annual Meeting of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
We present an annotation approach to capturing emotional and cognitive empathy in student-written peer reviews on business models in German. We propose an annotation scheme that allows us to model emotional and cognitive empathy scores based on three types of review components. Also, we conducted an annotation study with three annotators based on 92 student essays to evaluate our annotation scheme. The obtained inter-rater agreement of alpha=0.79 for the components and the multi-pi=0.41 for the empathy scores indicate that the proposed annotation scheme successfully guides annotators to a substantial to moderate agreement. Moreover, we trained predictive models to detect the annotated empathy structures and embedded them in an adaptive writing support system for students to receive individual empathy feedback independent of an instructor, time, and location. We evaluated our tool in a peer learning exercise with 58 students and found promising results for perceived empathy skill learning, perceived feedback accuracy, and intention to use. Finally, we present our freely available corpus of 500 empathy-annotated, student-written peer reviews on business models and our annotation guidelines to encourage future research on the design and development of empathy support systems.
The Potential of Technology-Mediated Learning Processes: A Taxonomy and Research Agenda for Educational Process Mining. Wambsganss, Thiemo; Schmitt, Anuschka; Mahning, Thomas; Ott, Anja; Soellner, Sigita; Ngo, Ngoc Anh; Geyer-Klingeberg, Jerome; Nakladal, Janina; Leimeister, Jan Marco. In International Conference on Information Systems (ICIS). Austin, Texas, USA, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Educational process mining (EPM) offers new possibilities to discover, monitor, improve, or predict students’ learning processes using data about their learning activities captured in technology-mediated information systems (IS). Although EPM has recently attracted considerable research interest, there is still limited shared knowledge about the distinctive design characteristics of EPM from an integrative perspective. To address this gap, we conducted a systematic literature review to identify EPM characteristics. Building on a technology-mediated learning perspective, we develop a taxonomy that classifies EPM characteristics into four major categories (i.e., purpose, user, input, analysis). We evaluate and refine our taxonomy with ten domain experts, identified three clusters in the reviewed literature, and derived six archetypes of EPM scenarios based on our categorization. Finally, we formulate a novel research agenda to guide researchers in systematizing and synthesizing research on different technological embeddings of EPM in a students’ learning process.
Design and Evaluation of an Adaptive Empathy Learning Tool. Wambsganss, Thiemo; Weber, Florian; Söllner, Matthias. In Proceedings of the 54th Hawaii International Conference on System Sciences. Hawaii International Conference on System Sciences, 2021.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Empathy is an elementary skill for daily interactions and for professional communication, agile teamwork and successful leadership and thus elementary for educational curricula. However, educational organizations face difficulties in providing the boundary conditions necessary for their students to develop empathy skills due to the lack of individual support in traditional large-scale and growing distance-learning scenarios. Drawing on cognitive dissonance theory, we propose an adaptive empathy learning tool that helps students develop their ability to react to other people's observed experiences through individual feedback in large-scale or distance learning scenarios. Based on a design science research project, we propose a set of design principles and instantiate and evaluate them with our prototype Eva in an online experiment with 65 students. The findings suggest that an adaptive empathy learning tool that follows our design principles is a promising approach to individually support students in their ability to react to other people's observed abilities in traditional learning scenarios.
Rethinking Food: Co-Creating Citizen Science for Sustainability Transition. Wilde, Daniel; Hupe, Anna; Trahan, Sahra; Guinita Abel, Caroline; Kjærsgaard Longueval, Solvejg; McLaughlin, Corey. In Nordes (Nordic Design Conference), S. 228–237. Kolding, Denmark, 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Transforming human food practices to be more sustainable is not straightforward. The human food system and international sustainability advice are both global in scope. Whereas food practices are locally situated and personal. ReThinking Food grapples with this challenge, using co-creative citizen science and the Future 50 Foods Report. The research involves cooking with; sharing food, recipes and stories; surveys, interviews, online and in-person activities. Through these actions, participants exchange knowledges with the food, their families and each other; become agents of change in their social groups and workplaces. They enact agency, shifting scales from human to non- human; near to far; from one-to-few-to-many. Building on this insight, we propose a hybrid engagement strategy for fostering connections across scales, from the personal to the planetary. The strategy strengthens the effectiveness of bottom-up societal transformation efforts.
Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution. Zernetsch, Stefan; Schreck, Steven; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), S. 2620–2626. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information. Zernetsch, Stefan; Trupp, Oliver; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In IEEE International Smart Cities Conference (ISC2), S. 1–7. IEEE, 2021.
- [ DOI ]
- [ BibSonomy-Post ]
The Influence of AI-Based Chatbots and Their Design on Users’ Trust and Information Sharing in Online Loan Applications. Zierau, Naim; Flock, Korbinian; Janson, Andreas; Söllner, Matthias; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2021.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Based on recent advances in Artificial Intelligence (AI), chatbots are now increasingly offered as an alternative source of customer service. For their uptake user trust in critical. However, little is known about how these interfaces fundamentally influence trust perceptions. In particular, it’s unclear what exactly causes perceptual differences - the change towards a conversational interface or the usage of anthropomorphic design elements. In this study, an online experiment with 160 participants was conducted to examine the differential effects of conversational interaction and anthropomorphism on trust in the interface or the provider within the context of online loan applications. The results show that both treatment conditions affect trust in the interface and the provider by increasing perceptions of social presence. Meanwhile, trust in the interface significantly effects the intention to share information, while trust in the provider has no effect on behavioral intention.

2020[ to top ]

Camera vs. Cooperative VRU Collision Avoidance. Bachmann, Marek; Morold, Michel; Engel, Sebastian; Götz, Johann; David, Klaus. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), S. 1–5. 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Theory-Motivated Design for Developing Privacy Nudges. Barev, Torben Jan. In International Conference on Wirtschaftsinformatik (WI). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Using digital technologies, various data traces are left behind for collection, storage and analysis. Potential risks that the availability of personal information entails, like the vulnerability to discrimination, commercial exploitation and unwanted monitoring, is ubiquitous. Hence, modern IT systems are needed that ensure employees' privacy and informational self-determination. One mechanism to achieve this is the implementation of privacy nudges in modern working systems. Nudging is a mechanism to influence decisions in a predictable way. In this context, privacy nudging concepts should influence employees` behavior in digital working environments in such a way that they make more data protection-friendly decisions. In this research project I am focusing on building an integrative understanding of effective nudging in privacy-related decisions. From this, design knowledge for better privacy nudges in digital work systems should be derived, which can pave the way for more privacy-sensitive IT systems. Successfully implemented privacy nudges can increase acceptance, trust and usage of modern IT-systems. Privacy sensitive IT-systems can then constitute a competitive advantage for the company. On the side of society, informational self-determination can be ensured and the potential risks that the availability of personal information entails can be reduced.
Designing Effective Privacy Nudges in Digital Environments: A Design Science Research Approach. Barev, Torben Jan; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Design Science Research in Information Systems and Technology (DESRIST), S. 388–393. Springer, Cham - Vinton G. Cerf Award., 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
When using digital technologies, various data traces are left behind for collection, storage and analysis. Innovative solutions for information systems are needed that mitigate privacy risks and foster information privacy. One mechanism to achieve this is using privacy nudges. Nudges are a concept from behavioral eco-nomics to influence individual’s decisions. However, many nudges show low or at least less effects than choice architects hope for and expect. Therefore, this de-sign science research (DSR) project focusses on developing evidence-based de-sign principles for privacy nudges to improve their effectiveness and pave the way for more privacy sensitive IT systems. In this context, we adopt a DSR ap-proach from Vaishnavi & Kuechler. From a theoretical perspective, we are con-tributing to the discussion of what drives privacy sensitive behavior. We extend generic nudge design models, making them applicable in the context of data dis-closure. For practitioners, we provide guidance on how to design and implement effective privacy nudges in the user interface of digital work systems.
Which Motivations Boost Idea Quality? Exploring the Impact of Customers’ Motives for Participating in Virtual Ideas Communities on Ideation Outcome. Bretschneider, Ulrich. In European Conference on Information Systems (ECIS). Marrakesch, Marokko, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
For practice it is important to leverage ideas of high quality from Virtual Ideas Communities (VIC). Therefore, firms that run such VIC have a strong interest in understanding which factors impact customers’ ideation outcome. This research investigates the influence of customers’ motivation factors for developing ideas on the quality of their ideas. So far, empirical studies that provide evidence on this association are neglected, although these insights would be highly beneficial for firms in their role as operator of VIC. Knowing the factors that have a positive influence will provide valuable insights into how to design effective incentive strategies that attract corresponding customer motivations and, in turn, will lead to higher levels of idea quality. In this research-in-progress paper we build a theoretical model explaining which of customers‘ motives for developing ideas have a positive impact on their ideation outcome.
Diversifying Smart Home Contexts. Dankwa, Nana Kesewaa. In Proceedings of 18th European Conference on Computer-Supported Cooperative Work. European Society for Socially Embedded Technologies (EUSSET), 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Advances in smart home technological innovation over the years has seen an increase in consumer interests. However, research contexts for smart homes tend to skew towards “traditional”living and housing situations. Through my Ph.D. research, I raise awareness of the need to consider other user contexts and living situations. I do this by exploring opportunities for smart home innovation with elderly women who live alone. I work with the elderly women to understand their values, needs, and collaboratively create new smart home devices. The outcome of my research would be smart home devices that support the lives and contexts of elderly women living alone.
Investigating Smart Home Needs for Elderly Women Who Live Alone. An Interview Study. Dankwa, Nana Kesewaa. In HCI International 2020 - Late Breaking Posters - 22nd International Conference, HCI 2020, Copenhagen, Denmark, July 19-24, 2020, Proceedings, Part II, Bd. 1294 von Communications in Computer and Information Science, C. Stephanidis, M. Antona, S. Ntoa (Hrsg.), S. 32–38. Springer, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Identity aspects such as gender, race, culture, and socio-economic status should be considered when technologies are designed with and for persons [9]. HCI research in ageing populations can benefit from considering the complexity of identity, use and context of older persons. This short paper draws attention to gender as an aspect of identity in working with ageing populations. It presents results from an interview study with elderly women who live alone in Germany. This study is part of a larger research project dedicated to innovating smart home technologies with and for elderly women who live alone. The research project has comprised of an “exploratory getting-to know each other” session, use experience of a smart speaker and interview studies. This paper presents insights from semi-structured interviews with 7 elderly women who live alone. These insights are also presented as design considerations for smart home technology for elderly women living alone. The study is the basis for further work with the elderly women, which are co-creation sessions to design smart home devices and develop prototypes.
Towards a New Methodology to Capture the Legal Compatibility of Conversational Speech Agents. Dickhaut, Ernestine; Thies, Laura Friederike; Janson, Andreas; Roßnagel, Alexander; Leimeister, Jan Marco. In Conference on Conversational User Interfaces (CUI). 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Higher legal standards with regards to the data protection of individuals such as the EU General Data Protection Regulation (EU-GDPR) are increasing the pressure on developers of IT artifacts. This is especially prevalent when considering conversational speech agents (CSA), which are collecting data in new ways and thus are oftentimes producing conflicts with existing law regulations. For this purpose, we introduce the law simulation method, which is a well-known evaluation method among law researchers for capturing the legal compatibility of IT artifacts such as CSA. With this rigorous method, we are able to derive actionable guidance for CSA developers to evaluate developer efforts for increasing legal compatibility. To illustrate our methodological approach, we describe in this paper key steps of the method with respect to the evaluation of CSA. We briefly discuss how this procedure can serve as the foundation for a new evaluation method of legally compatible systems in information systems.
Judging Alexa - Towards a New Methodology to Capture the Legal Compatibility of Conversational Speech Agents. Dickhaut, Ernestine; Thies, Laura Friederike; Janson, Andreas; Roßnagel, Alexander; Leimeister, Jan Marco. In Conference on Conversational User Interfaces (CUI), S. 1–4. 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Higher legal standards with regards to data protection of individuals such as EU-GDPR are increasing the pressure on developers of IT artifacts. This is especially prevalent when considering conversational speech agents (CSA) that are collecting data in new ways, and thus, are oftentimes producing conflicts with existing law regulations. For this purpose, we introduce the law simulation method which is a well-known evaluation method among law researchers for capturing legal compatibility of IT artifacts such as CSA. With this rigorous method, we are able to derive actionable guidance for CSA developers to evaluate developer efforts for increasing legal compatibility. To illustrate our methodological approach, we describe in this workshop paper key steps of the method with respect to the evaluation of CSA. We discuss how this can serve as the foundation for a new evaluation method of legally compatible systems in information systems.
"Boundaries Do Not Sit Still" from Interaction to Agential Intra-action in HCI. Draude, Claude. In Human-Computer Interaction. Design and User Experience, Bd. 12181 von Lecture Notes in Computer Science, M. Kurosu (Hrsg.), S. 20–32. Springer International Publishing, Copenhagen, Denmark, 2020.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
We live in a world that is increasingly shaped through computational technology. The expansion and pervasiveness of computing brings along opportunities and challenges for the field of HCI. New application domains evolve and technological advances pose novel interaction possibilities. But with computing's shaping power comes also the need for increased responsibility and attention to the societal, political and ecological impact of technology. In this conceptual paper, new materialist thinking is employed to locate these societal etc. aspects as inextricably enmeshed within computing research and development. New materialism is a multi-vocal, cross-disciplinary field of doing-thinking. In contrast to Western dichotomic tradition, a monistic, post-anthropocentric perspective is provided and matter as an active agent in world-making is acknowledged. Central to this paper is the questioning of the human and computer dichotomy at the core of the field of HCI. For this, a material-semiotic perspective on human-computer interaction is elaborated upon. Furthermore, the paradigm of interaction is revisited and reworked as a conception of agential intra-action, a term coined by physicist Karen Barad. From this interrogation of dichotomies and the notion of intra-action follow further conceptual shifts that are discussed as productive for the future of HCI, namely responsibility as specification of ethical agency and performativity in contrast to representationalism.
Doing Agile vs. Being Agile - Understanding Their Effects to Improve Agile Work. Eilers, Karen; Simmert, Benedikt; Peters, Christoph. In International Conference on Information Systems (ICIS). ICIS Proceedings, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Companies show a growing demand in corporate agility. The effects of so-called doing and being agile are the key for positive outcomes in agile work. Scrum is used by companies to make them more agile. The present study examines the interaction of doing agile (leadership, work design) and being agile (individual characteristics, empowerment) in relation to satisfaction and commitment based on an online survey of 129 Scrum development team members. The results show that work design and leadership impact empowerment and that the latter leads to both job satisfaction and commitment. Team orientation has no effect. Openness for new actions moderates the relationship between work design and the outcome variables. The results can be used in practice to increase the satisfaction and commitment within Scrum. They provide an insight into the impact structure within Scrum and are thus also the basis for future research.
Let’s Team Up: Designing Conversational Agents as Teammates. Elshan, Edona; Ebel, Philipp. In International Conference on Information Systems (ICIS). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The success of projects is, amongst others, highly depended on the team members skillset and ability to collaborate. Hence, education has to undergo a change to keep up with the shift in the compositions of skills and knowledge needed for students. To overcome scalability issues, we propose to develop Timmy-a conversational agents (CAs) that acts as a team member. As there is a lack of concrete design knowledge concerning CAs as peers in teams, we conduct a design science research project. Based on requirements from scientific literature and expert interviews, we develop a concise set of design principles for designing CAs in peer roles in educational settings. Furthermore, we present an initial proof of concept evaluation. These insights will support researchers and practitioners to understand better how CAs can be systematically built to ameliorate the collaborative skill of students in teamwork settings.
Evaluation einer Augmented-Reality-Anleitung für eine komplexe Montageaufgabe. Funk, J.; Schmidt, L. In DELFI 2020: 18. Fachtagung Bildungstechnologien (Online 2020), von Lecture Notes in Informatics (LNI) - Proceedings, R. Zender, D. Ifenthaler, T. Leonhardt, C. Schumacher (Hrsg.), S. 25–36 *** Best Paper Award ***. Gesellschaft für Informatik, Bonn, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die vorliegende Studie vergleicht den Einsatz einer markerbasierten AR-Anleitung mit einer in der manuellen Montage üblichen Papieranleitung. Es wurden die Hypothesen geprüft, ob sich die Anleitungsart auf die Montagezeit, die Anzahl der Fehler, die Gebrauchstauglichkeit und die Beanspruchung der Mitarbeiter auswirkt. Statt mit studentischen Stichproben und künstlichen Montageaufgaben (z. B. Legobaugruppen) wurde die Studie mit 16 Auszubildenden an einem realen Arbeitsplatz für die Montage von Notgriffen zur Türentriegelung in Schienenfahrzeugen durchgeführt. Es wurden fünf Montagedurchgänge durchgeführt. Die Montagezeit und die gemachten Fehler wurden aus Videoaufzeichnungen ermittelt. Die Gebrauchstauglichkeit (SUS) und die Beanspruchung (NASA-TLX) wurden mit Fragebögen erhoben. Nachdem die AR-Gruppe zu Beginn langsamer montierte als die Papier-Gruppe, war diese im fünften Durchgang signifikant schneller. Die vergleichbare Fehleranzahl, Gebrauchstauglichkeit und Beanspruchung machen markerbasierte AR-Anwendungen besonders durch den leichten Einstieg und die geringen Kosten interessant für die Wissensvermittlung in der manuellen Montage.
Vergleichende Usability-Evaluation einer Lernplattform. Funk, J.; Schmidt, L. In Digitaler Wandel, digitale Arbeit, digitaler Mensch? 66. Kongress der Gesellschaft für Arbeitswissenschaft (Berlin 2020), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (C.8.1). GfA-Press, Dortmund, 2020.
- [ Abstract ]
- [ BibSonomy-Post ]
Im Rahmen der hier vorgestellten Studie wurden die Gebrauchstauglichkeit, die Gestaltung und der Aufbau einer zuvor an die Bedürfnisse der Lernenden angepassten Lernplattform bei Nutzung mit typischen Aufgaben, wie der Anmeldung mit Login-Daten, im Vergleich zu der unveränderten Moodle-Lernplattform untersucht. Neben Fragebögen für die Gebrauchstauglichkeit (SUS), die visuelle Gestaltung (VisAWI) und den Aufbau und die Struktur der Lernplattform wurden die Aufgabenerfüllung (Effektivität) und die dafür benötigten Zeiten (Effizienz) sowie teilweise Blickbewegungsdaten erfasst. Mit 29 Studienteilnehmenden zeigten sich keine signifikanten Unterschiede.
Normal-Wishart clustering for novelty detection. Gruhl, Christian; Schmeißing, Jörn; Tomforde, Sven; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 64–69. IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Continuous Learning of Deep Neural Networks to Improve Forecasts for Regional Energy Markets. He, Yujiang; Henze, Janosch; Sick, Bernhard. In International Federation of Automatic Control (IFAC) World Congress, S. 12175–12182. Elsevier, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Verbesserung eines omnidirektionalen Laufeingabegerätes für die virtuelle Realität. Hegenberg, J.; Krause, P.; Schmidt, L. In Digitaler Wandel, digitale Arbeit, digitaler Mensch? 66. Kongress der Gesellschaft für Arbeitswissenschaft (Berlin 2020), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.1.2). GfA-Press, Dortmund, 2020.
- [ Abstract ]
- [ BibSonomy-Post ]
Ein Prototyp eines omnidirektionalen Laufeingabegerätes wurde insbesondere hinsichtlich des Regelungskonzeptes auf Basis von Empfehlungen aus der Literatur optimiert. Der Beitrag stellt die relevanten Rahmenbedingungen des Einsatzes solcher Systeme vor und berichtet über die Ergebnisse einer vergleichenden Studie, die auf die Verbesserung der Nutzung, insbesondere bzgl. der Regelung der translatorischen und der rotatorischen Bewegungsrichtung, abzielt. Dabei wurden zwei neuentwickelte Regelungsvarianten der bestehenden Lösung des Herstellers gegenübergestellt. Die Effekte wurden mit gängigen Standardfragebögen sowie Befragungsinstrumenten zu anderen Laufeingabegeräten untersucht. Es konnte ein signifikanter Vorteil des neuen Regelungskonzeptes belegt werden.
Representation Learning in Power Time Series Forecasting. Henze, Janosch; Schreiber, Jens; Sick, Bernhard. In Deep Learning: Algorithms and Applications, W. Pedrycz, S.-M. Chen (Hrsg.), S. 67–101. Springer International Publishing, 2020.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
A Self-Organizing Multi-Agent Knowledge Base. Jakob, Stefan; Jahl, Alexander; Baraki, Harun; Geihs, Kurt. In The IEEE 2020 International Conference on Web Services (ICWS 2020). IEEE, 2020.
- [ BibSonomy-Post ]
Reframing AX with Critical Design: The Potentials and Limits of Algorithmic Experience as a Critical Design Concept. Klumbyte, Goda; Lücking, Phillip; Draude, Claude. In Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society, von NordiCHI ’20. Association for Computing Machinery, Tallinn, Estonia, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This paper investigates how Algorithmic Experience (AX) can be used as a conceptual tool to help make algorithms and experiences of them visible through systems design and how interactions might be designed in order to elicit conscious and critical examination. Can algorithmic systems be positioned as critical artifacts? If so, to what extent? The paper reflects on interactions between users and the Social Privilege Estimator– a social scoring system based on facial recognition and classification that was built as a critical design artifact in order to raise awareness of existing inequalities and adverse effects of facial recognition systems. We argue that critical design can and should be used for AX and human-algorithm interaction design in order to support algorithmic literacy and critical capacity of the users and we suggest some conceptual reframings of AX towards this goal.
Reframing AX with Critical Design: The Potentials and Limits of Algorithmic Experience as a Critical Design Concept. Klumbytė, Goda; Lücking, Phillip; Draude, Claude. In Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society, von NordiCHI ’20, S. 1–12. Association for Computing Machinery, New York, NY, USA, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
This paper investigates how Algorithmic Experience (AX) can be used as a conceptual tool to help make algorithms and experiences of them visible through systems design and how interactions might be designed in order to elicit conscious and critical examination. Can algorithmic systems be positioned as critical artifacts? If so, to what extent? The paper reflects on interactions between users and the Social Privilege Estimator– a social scoring system based on facial recognition and classification that was built as a critical design artifact in order to raise awareness of existing inequalities and adverse effects of facial recognition systems. We argue that critical design can and should be used for AX and human-algorithm interaction design in order to support algorithmic literacy and critical capacity of the users and we suggest some conceptual reframings of AX towards this goal.
Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks. Kress, V.; Schreck, S.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI), S. 2723–2730. IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Gebrauchstauglichkeit einer Augmented-Reality-Reiseassistenzanwendung und Vergleich mit herkömmlicher Unterstützung in einem Echtweltszenario. Mack, N. A.; Schmidt, L. In Digitaler Wandel, digitale Arbeit, digitaler Mensch? 66. Kongress der Gesellschaft für Arbeitswissenschaft (Berlin 2020), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.3.4). GfA-Press, Dortmund, 2020.
- [ Abstract ]
- [ BibSonomy-Post ]
Im Rahmen des Projektes RadAR+ wurde eine Augmented-Reality-(AR)-Reiseassistenzanwendung für eine Datenbrille entwickelt und prototypisch umgesetzt, welche ein Routing für den öffentlichen Verkehr sowie eine AR-Fußgängernavigation vereint und dadurch eine vollständige Navigation vom Start- zum Zielort ermöglicht. Der Prototyp wurde in einem Echtweltszenario mit 37 Probanden vergleichend zur herkömmlichen Unterstützung evaluiert. Es konnte gezeigt werden, dass die Gebrauchstauglichkeit der AR-Reiseassistenzanwendung von den Probanden als "gut" bewertet wird. Des Weiteren ist feststellbar, dass keine signifikanten Unterschiede zwischen der subjektiv empfundenen Beanspruchung beim Prototyp und der herkömmlichen Unterstützung bestehen. Jedoch gab es eine signifikant geringere Schrittzahl bei der Gruppe, die das Reiseassistenzsystem nutzte.
Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm. Meier, David; Hartmann, Gregor; Völker, Jens; Viefhaus, Jens; Sick, Bernhard. In Advances in Computational Methods for X-Ray Optics V, S. 71–77. SPIE, 2020.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Mandate-driven Networking Eco-system: A Paradigm Shift in End-to-End Communications. Moerman, Ingrid; Zeghlache, Djamal; Shahid, Adnan; Santos, Joao F.; DaSilva, Luiz A.; David, Klaus; Farscrotu, John; de Ridder, Ad; Liu, Wei; Hoebeke, Jeroen. In 2020 2nd 6G Wireless Summit (6G SUMMIT), S. 1–6. 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Requirements on Delay of VRU Context Detection for Cooperative Collision Avoidance. Morold, Michel; Nguyen, Quang-Huy; Bachmann, Marek; David, Klaus; Dressler, Falko. In 2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall), S. 1–5. 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Crowdworking Platforms in Germany: Business Insights from a Study & Implications for Society. Mrass, Volkmar; Peters, Christoph; Leimeister, Jan Marco. In Jahrestagung des Verbands der Hochschullehrer für Betriebswirtschaft (VHB). Frankfurt am Main, Germany, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The competitiveness of organizations and whole economies depends on how successfully they are able to cope with the digital transformation and new technological trends. In the area of digital work, crowdworking platforms emerged as intermediaries that support a new form of service delivery and work organization. Despite their increasing importance, there is only few data about key characteristics of such platforms such as number of employees or revenues. Furthermore, extant data often focusses only on a few platforms, mostly from the US. Based on results from a study about the 32 crowdworking platforms that have their headquarters or a physical location in Germany, we provide data that for the first time allows to draw conclusions for the “total population” of crowdworking platforms in a defined larger region (Germany as Europe’s largest and the world fourth largest economy). These results are valuable for various stakeholders from economy and politics, allowing them to make economic or political decisions on a more informed basis. Furthermore, we develop an evaluation framework that depicts the implications for these groups along the dimensions costs, flexibility, “humanity”, quality, and time: Crowdworking platforms on the one hand provide several opportunities: Individuals gain more flexibility, groups can benefit from additional contributors, organizations have the potential to process work faster and cheaper. On the other hand, this novel form of work organization also includes potential threats for all groups: Low payments and ‘tayloristic’ work, insufficient quality or irritation of internal employees. Based on 12 interviews with company representatives and crowdworkers, we evaluate implications of this novel form of work organization for society.
Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar. Scheiner, Nicolas; Kraus, Florian; Wei, Fangyin; Phan, Buu; Mannan, Fahim; Appenrodt, Nils; Ritter, Werner; Dickmann, Jurgen; Dietmayer, Klaus; Sick, Bernhard; Heide, Felix. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Off-the-shelf sensor vs. experimental radar - How much resolution is necessary in automotive radar classification?. Scheiner, Nicolas; Schumann, Ole; Kraus, Florian; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE International Conference on Information Fusion (FUSION), S. 1–8. IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Understanding User Preferences of Digital Privacy Nudges – A Best-Worst Scaling Approach. Schöbel, Sofia; Barev, Torben Jan; Janson, Andreas; Hupfeld, Felix; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Digital nudging in privacy has become more important to protect users of information systems while working with privacy-related data. Nudging is about altering a user’s behavior without forbidding any options. Several approaches exist to “nudge” users to change their behavior. Regarding the usage of digital privacy nudges, research still has to understand the meaning and relevance of individual nudges better. Therefore, this paper compares the preferences of users for different digital nudges. To achieve this goal, it presents the results of a so-called best-worst scaling. This study contributes to theory by providing a better understanding of user preferences regarding design variations of digital nudges. We support practitioners by giving implications on how to design digital nudges in terms of user preferences.
Leaders, Empower Your Workforce! Analyzing Leadership in Internal Crowd Work. Simmert, Benedikt; Peters, Christoph. In Academy of Management Annual Meeting (AOM). 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
New digital and agile forms of work organization require new leadership styles and competencies. Still, the understanding of leadership in these new forms of work is in its infancy. We select internal crowd work (ICW) as one, clearly defined new form of work and increase understanding of leadership in this context by analyzing four distinct cases of ICW. Based on qualitative interviews, we describe how employees perceive psychological empowerment and develop workforce agility through different leadership styles in ICW. As our main contribution, we detail and extend existing research regarding ICW and empowerment by identifying structural antecedents that affect psychological empowerment of ICW as well as consequences of an empowered workforce in ICW. Thereby, we indicate that an empowered workforce is an important factor for the implementation of workforce agility in ICW. Moreover, regarding leadership, we explain the design and changes of leadership in ICW in detail and explicate a new requirement for leaders in agile and digital form of work organization: the flexible handling of different context-specific situations, projects and tasks. For this purpose, we develop a theoretical model that describes the effects of shared leadership, empowering leadership and e-leadership on workforce agility mediated by an empowered workforce.
Same Same But Different? A Two-Foci Perspective on Trust in Information Systems. Söllner, Matthias. In Proceedings of the 53rd Hawaii International Conference on System Sciences. Hawaii International Conference on System Sciences, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Trust is one of the most important factors driving the adoption and use of information systems. The goal of this paper is to provide a first evaluation of a conceptual piece claiming a) that users distinguish between their trust in an IS and the provider of this IS and b) that both kinds of trust are important for the success sustainable success of IS providers. To evaluate the claims, a research model is developed and evaluated using data of 234 students during the introduction of a new IS at an European university. The results provide support for both claims, since the correlation between the two trust constructs is low, and the nomological networks differ. Regarding the importance of both constructs, trust in the IS is found to have an important impact of the use of the IS, whereas trust in the provider is a major driver of the users’ loyalty.
Orometric Methods in Bounded Metric Data. Stubbemann, Maximilian; Hanika, Tom; Stumme, Gerd. In Advances in Intelligent Data Analysis XVIII - 18th International Symposium on Intelligent Data Analysis, IDA 2020, Konstanz, Germany, April 27-29, 2020, Proceedings, Bd. 12080 von Lecture Notes in Computer Science, M. R. Berthold, A. Feelders, G. Krempl (Hrsg.), S. 496–508. Springer, 2020.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Fairness, performance, and robustness: is there a cap theorem for self-adaptive and self-organising systems?. Tomforde, Sven; Gruhl, Christian. In Workshop on Self-Improving System Integration (SISSY), ACSOS, S. 54–59. IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
A swarm-fleet infrastructure as a scenario for proactive, hybrid adaptation of system behaviour. Tomforde, Sven; Gruhl, Christian; Sick, Bernhard. In Workshop on Self -Aware Computing (SeAC), ACSOS, S. 166–169. IEEE, 2020.
- [ DOI ]
- [ BibSonomy-Post ]
Unlocking Transfer Learning in Argumentation Mining: A Domain-Independent Modelling Approach. Wambsganss, Thiemo; Molyndris, and Nikolaos; Söllner, Matthias. In 15th International Conference on Wirtschaftsinformatik (WI), S. 341–356. 2020.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
AL: An Adaptive Learning Support System for Argumentation Skills. Wambsganss, Thiemo; Niklaus, Christina; Cetto, Matthias; Söllner, Matthias; Handschuh, Siegfried; Leimeister, Jan Marco. In CHI ’20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, R. Bernhaupt, F. ’Floyd’ Mueller, D. Verweij, J. Andres, J. McGrenere, A. Cockburn, I. Avellino, A. Goguey, P. Bjøn, S. Zhao, B. P. Samson, R. Kocielnik (Hrsg.), S. 1–14. ACM, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Recent advances in Natural Language Processing (NLP) bear the opportunity to analyze the argumentation quality of texts. This can be leveraged to provide students with individual and adaptive feedback in their personal learning journey. To test if individual feedback on students' argumentation will help them to write more convincing texts, we developed AL, an adaptive IT tool that provides students with feedback on the argumentation structure of a given text. We compared AL with 54 students to a proven argumentation support tool. We found students using AL wrote more convincing texts with better formal quality of argumentation compared to the ones using the traditional approach. The measured technology acceptance provided promising results to use this tool as a feedback application in different learning settings. The results suggest that learning applications based on NLP may have a beneficial use for developing better writing and reasoning for students in traditional learning settings.
A Corpus for Argumentative Writing Support in German. Wambsganss, Thiemo; Niklaus, Christina; Söllner, Matthias; Handschuh, Siegfried; Leimeister, Jan Marco. In 28th International Conference on Computational Linguistics (COLING). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In this paper, we present a novel annotation approach to capture claims and premises of arguments and their relations in student-written persuasive peer reviews on business models in Ger-man language. We propose an annotation scheme based on annotation guidelines that allows to model claims and premises as well as support and attack relations for capturing the structure of argumentative discourse in student-written peer reviews. We conduct an annotation study with three annotators on 50 persuasive essays to evaluate our annotation scheme. The obtained inter-rater agreement of α = 0.57 for argument components and α = 0.49 for argumentative relations indicates that the proposed annotation scheme successfully guides annotators to moderate agreement. Finally, we present our freely available corpus of 1,000 persuasive student-written peer reviews on business models and our annotation guidelines to encourage future research on the design and development of argumentative writing support systems for students.
Design and Evaluation of an Adaptive Dialog-Based Tutoring System for Argumentation Skills. Wambsganss, Thiemo; Söllner, Matthias; Leimeister, Jan Marco. In International Conference on Information Systems (ICIS 2020). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recent advances in Natural Language Processing not only bear the opportunity to design new dialog-based forms of human-computer interaction but also to analyze the argumentation quality of texts. Both can be leveraged to provide students with individual and adaptive tutoring in their personal learning journey to develop argumentation skills. Therefore, we present the results of our design science research project on how to design an adaptive dialog-based tutoring system to help students to learn how to argue. Our results indicate the usefulness of an adaptive dialog-based tutoring system to support students individually, independent of a human instructor, time and place. In addition to providing our embedded software artifact, we document our evaluated design knowledge as a design theory. Thus, we provide the first step toward a nascent design theory for adaptive conversational tutoring systems to individual support metacognition skill education of students in traditional learning scenarios.
Systematische Entwicklung eines Lerntools zur Erhöhung der Argumentationsfähigkeiten von Studierenden. Wambsganss, Thiemo; Weber, Florian; Staufenberg, Tobias; Bott, Leopold; Söllner, Matthias. In 15th International Conference on Wirtschaftsinformatik (WI), S. 449–464. GITO Verlag, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Die Digitalisierung führt zu neuen Anforderungen an Fähigkeiten und Kenntnissen, die Studierende in ihrem zukünftigen Berufsleben benötigen. Metakognitive Lernkompetenzen und Higher Order Thinking Skills werden dabei immer wichtiger, um Herausforderungen der Zukunft zu lösen. Eine Unterklasse dieser Fähigkeiten, die wesentlich zu Kommunikation, Kollaboration und Problemlösung beiträgt, ist die Fähigkeit, strukturiert und reflektierend zu argumentieren. Bildungseinrichtungen haben jedoch Schwierigkeiten, die für die Entwicklung dieser Fähigkeit notwendigen Rahmenbedingungen zu schaffen. In diesem Paper stellen wir unser Design Science Research Projekt vor, in dem wir ein Lerntool entwickeln, dass es ermöglicht, Studierende durch intelligentes Feedback beim Erlernen von Argumentation zu unterstützen. Wir präsentieren dazu acht Designprinzipien, abgeleitet aus aktueller Literatur und aus 21 Nutzerinterviews, sowie einen evaluierten Prototyen als eine Form der Instanziierung dieser Prinzipien. Ziel unseres Forschungsprojektes ist es, ein Lerntool zu entwickeln, das Studierenden hilft, ihre Argumentationsfähigkeit durch individuelles Feedback zu verbessern.
Unleashing the Potential of Conversational Agents for Course Evaluations: Empirical Insights from a Comparison with Web Surveys. Wambsganss, Thiemo; Winkler, Rainer; Schmid, Pascale; Söllner, Matthias. In European Conference on Information Systems (ECIS) 2020. ECIS, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recent advances in Natural Language Processing (NLP) bear the opportunity to design new forms of human-computer interaction with conversational interfaces. However, little is known about how these interfaces change the way users respond in online course evaluations. We aim to explore the effects of conversational agents (CAs) on the response quality of online course evaluations in education compared to the common standard of web surveys. Past research indicates that web surveys come with disadvantages, such as poor response quality caused by inattention, survey fatigue or satisficing behavior. We propose that a conversational interface will have a positive effect on the response quality through the different way of interaction. To test our hypotheses, we design an NLP-based CA and deploy it in a field experiment with 176 students in three different course formats and compare it with a web survey as a baseline. The results indicate that participants using the CA showed higher levels of response quality and social presence compared to the web survey. These findings along with technology acceptance measurements suggest that using CAs for evaluation are a promising approach to increase the effectiveness of surveys in general.
Designing a Conversational Agent as a Formative Course Evaluation Tool. Wambsganss, Thiemo; Winkler, Rainer; Schmid, Pascale; Söllner, Matthias. In 15th International Conference on Wirtschaftsinformatik (WI), S. 1234–1249. 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Today’s graduating students face ever-changing environments when they enter their job life. Educational institutions must therefore continuously develop their course structure and content in order to prepare their students to be future employees. A very important means for developing the courses is the students’ course evaluations. Due to financial and organizational restrictions, these course evaluations are usually carried out quantitatively and at the end of the semester. However, past research has shown that this kind of evaluation faces certain constraints such as low acceptance rates, only time-related insights and low-quality answers that do not really help the lecturer to improve the course. Drawing on social response theory, we propose that conversational agents as a formative course evaluation tool are able to address the mentioned problems by interactively engaging with students. Therefore, we propose a set of design principles and evaluate them with our prototype Eva.
A Conversational Agent to Improve Response Quality in Course Evaluations. Wambsganss, Thiemo; Winkler, Rainer; Söllner, Matthias; Leimeister, Jan Marco. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, von CHI EA ’20, S. 1–9. Association for Computing Machinery, Honolulu, HI, USA, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Recent advances in Natural Language Processing (NLP) bear the opportunity to design new forms of human-computer interaction with conversational interfaces. We hypothesize that these interfaces can interactively engage students to increase response quality of course evaluations in education compared to the common standard of web surveys. Past research indicates that web surveys come with disadvantages, such as poor response quality caused by inattention, survey fatigue or satisficing behavior. To test if conversational interfaces have a positive impact on the level of enjoyment and the response quality, we design an NLP-based conversational agent and deploy it in a field experiment with 127 students in our lecture and compare it with a web survey as a baseline. Our findings indicate that using conversational agents for evaluations are resulting in higher levels of response quality and level of enjoyment, and are therefore, a promising approach to increase the effectiveness of surveys in general.
Lost in Translation: An Interactive Workshop Mapping Interdisciplinary Translations for Epistemic Justice. Wan, Evelyn; de Groot, Aviva; Jameson, Shazade; Păun, Mara; Lücking, Phillip; Klumbytė, Goda; Lämmerhirt, Danny. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, von FAT* ’20, S. 692. Association for Computing Machinery, Barcelona, Spain, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
There are gaps in understanding in and between those who design systems of AI/ ML, those who critique them, and those positioned between these discourses. This gap can be defined in multiple ways - e.g. methodological, epistemological, linguistic, or cultural. To bridge this gap requires a set of translations: the generation of a collaborative space and a new set of shared sensibilities that traverse disciplinary boundaries. This workshop aims to explore translations across multiple fields, and translations between theory and practice, as well as how interdisciplinary work could generate new operationalizable approaches. We define 'knowledge' as a social product (L. Code) which requires fair and broad epistemic cooperation in its generation, development, and dissemination. As a "marker for truth" (B. Williams) and therefore a basis for action, knowledge circulation sustains the systems of power which produce it in the first place (M. Foucault). Enabled by epistemic credence, authority or knowledge, epistemic power can be an important driver of, but also result from, other (e.g. economic, political) powers. To produce reliable output, our standards and methods should serve us all and exclude no-one. Critical theorists have long revealed failings of epistemic practices, resulting in the marginalization and exclusion of some types of knowledge. How can we cultivate more reflexive epistemic practices in the interdisciplinary research setting of FAT*? We frame this ideal as 'epistemic justice' (M. Geuskens), the positive of 'epistemic injustice', defined by M. Fricker as injustice that exists when people are wronged as a knower or as an epistemic subject. Epistemic justice is the proper use and allocation of epistemic power; the inclusion and balancing of all epistemic sources. As S. Jasanoff reminds us, any authoritative way of seeing must be legitimized in discourse and practice, showing that practices can be developed to value and engage with other viewpoints and possibly reshape our ways of knowing. Our workshop aims to address the following questions: how could critical theory or higher level critiques be translated into and anchored in ML/AI design practices - and vice versa? What kind of cartographies and methodologies are needed in order to identify issues that can act as the basis of collaborative research and design? How can we (un)learn our established ways of thinking for such collaborative work to take place? During the workshop, participants will create, share and explode prototypical workflows of designing, researching and critiquing algorithmic systems. We will identify moments in which translations and interdisciplinary interventions could or should happen in order to build actionable steps and methodological frameworks that advance epistemic justice and are conducive to future interdisciplinary collaboration.
Does Context Matter for Value Co-Creation in Smart Learning Services?. Weinert, Tim; Janson, Andreas; Leimeister, Jan Marco. In International Conference on Wirtschaftsinformatik (WI), N. Gronau, H. Krasnova, K. Pousttchi, M. Heine (Hrsg.). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Smart learning services offer customized learning solutions by systematically considering the context of the learner. However, it is still unclear how the value co-creation within smart learnings is affected by context considerations. Therefore, it is important to understand how the context can influence the value co-creation potential in smart learning services. To investigate how context shapes value co-creation smart learning services, we first conduct a systematic literature review to investigate context factors within learning processes. Afterwards, we develop a conceptual model to explain how context in smart learning systems can be used to enhance the co-creation potential in learning processes. Overall, we provide a better understanding of context considerations in service systems as a theoretical contribution of our conceptual investigation. Finally, we provide practical implications for educational service providers for designing smart learning services under the specific consideration of different contexts
Towards Co-Creation of Learning Material in Vocational Training. Weinert, Tim; Thiel de Gafenco, Marian. In European Conference on Information Systems (ECIS). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The complexity of production processes increased during the last years, especially due to digitalization, which results in an increasing need of in-company trainings. Hence, companies use trainings to impart action-oriented knowledge in the work process. However, these trainings are often supported by learning materials that do not reflect the current work situation of the employees because they are either outdated or too general. We are addressing this problem using a co-creation process by enabling em- ployees to generate the materials independently during the work process. Within the framework of a theory-driven design science research approach, we derived requirements from theory as well as from a focus group workshop and a work process analysis to develop design elements for this process. We pay particular attention to the cognitive load (CL) of the employees. The theoretical contribution of our research is twofold: On the one hand, we give insights regarding the effects of the physical environment on CL. On the other hand, we give insights about how to design systems that can avoid CL within knowledge generation processes. In this way, we help practitioners to design systems that consider the CL of employees.
Fostering Interaction in Higher Education with Deliberate Design of Interactive Learning Videos. Weinert, Tim; Thiel de Gafenco, Marian; Börner, Niklas. In International Conference on Information Systems (ICIS), J. F. George, S. Paul, R. De´ (Hrsg.). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Interactive learning videos are increasingly used in higher education. By using interactive elements, learners can be actively involved in the learning process to enhance their interactions with the content, other learners, and the teacher. However, there are significant gaps in the design of such interactive learning videos: Mostly, instructors do not know which interaction elements they should use where in the video to support the learning process of their students. Based on a design science research approach, we develop reference guidelines to support developers in creating interactive learning videos in higher education that improve the interaction of learners. Based on Interaction Theory and a systematic collection of requirements from theory and practice, we identify research gaps and try to address them with our reference guidelines. Hence, we contribute to theory by providing generalizable reference guidelines for the development of interactive learning videos in higher education.
SPAM - A Process Model for Developing Smart Personal Assistants. Winkler, Rainer; Elshan, Edona; Söllner, Matthias; Leimeister, Jan Marco. In HICSS, S. 1–10. HICSS, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Information technology capabilities are growing at an impressive pace and increasingly overstrain the cognitive abilities of users. User assistance systems such as online manuals try to help the user in handling these systems. However, there is strong evidence that traditional user assistance systems are not as effective as intended. With the rise of smart personal assistants, such as Amazon’s Alexa, user assistance systems are becoming more sophisticated by offering a higher degree of interaction and intelligence. This study proposes a process model to develop Smart Personal Assistants. Using a design science research approach, we first gather requirements from Smart Personal Assistant designers and theory, and later evaluate the process model with developing an Amazon Alexa Skill for a Smart Home system. This paper contributes to the existing user assistance literature by offering a new process model on how to design Smart Personal Assistants for intelligent systems.
Engaging Learners in Online Video Lectures with Dynamically Scaffolding Conversational Agents. Winkler, Rainer; Hobert, Sebastian; Fischer, Tizian; Salovaara, Antti; Söllner, Matthias; Leimeister, Jan Marco. In European Conference on Information Systems (ECIS) 2020. ECIS, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Online education creates new opportunities for learners, which has led to sharply increasing enrollment in the last few years. Despite these benefits, past research shows that the lack of individual interaction with educators creates low learner engagement that leads to high attrition rates, which remains a major challenge in the field. Dynamically scaffolding conversational agents built into online video lectures promise to address this problem by individually interacting with learners, similar to educators’ scaffolding behavior. These agents are equipped with recent natural language processing capabilities, creating human-like conversations that help learners to be more engaged in the learning process. To test our hypothesis, we built a dynamically scaffolding conversational agent named Sara and compared it with an often-implemented static conversational agent built into two online video lectures. We deployed a lab experiment with 182 learners. The neurophysiological measurements revealed that Sara significantly improved learner engagement partly explained by differences in learners’ perceptions in the way they experienced the interaction. This study connects to already existing conversational agent studies in online education and highlights the importance of including dynamically scaffolding conversational agents in online video lectures to address the problem of low learner engagement in online education.
Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agents. Winkler, Rainer; Hobert, Sebastian; Salovaara, Antti; Söllner, Matthias; Leimeister, Jan Marco. In Computer Human Interaction Conference (CHI). 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Enrollment in online courses has sharply increased in higher education. Although online education can be scaled to large audiences, the lack of interaction between educators and learners is difficult to replace and remains a primary challenge in the field. Conversational agents may alleviate this problem by engaging in natural interaction and by scaffolding learners’ understanding similarly to educators. However, whether this approach can also be used to enrich online video lectures has largely remained unknown. We developed Sara, a conversational agent that appears during an online video lecture. She provides scaffolds by voice and text when needed and includes a voice-based input mode. An evaluation with 182 learners in a 2 x 2 lab experiment demonstrated that Sara, compared to more traditional conversational agents, significantly improved learning in a programming task. This study highlights the importance of including scaffolding and voice-based conversational agents in online videos to improve meaningful learning.
Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent. Winkler, Rainer; Hobert, Sebastian; Salovaara, Antti; Söllner, Matthias; Leimeister, Jan Marco. In CHI ’20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, R. Bernhaupt, F. ’Floyd’ Mueller, D. Verweij, J. Andres, J. McGrenere, A. Cockburn, I. Avellino, A. Goguey, P. Bjøn, S. Zhao, B. P. Samson, R. Kocielnik (Hrsg.), S. 1–14. ACM, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Enrollment in online courses has sharply increased in higher education. Although online education can be scaled to large audiences, the lack of interaction between educators and learners is difficult to replace and remains a primary chal-lenge in the field. Conversational agents may alleviate this problem by engaging in natural interaction and by scaffold-ing learners’ understanding similarly to educators. However, whether this approach can also be used to enrich online video lectures has largely remained unknown. We developed Sara, a conversational agent that appears during an online video lecture. She provides scaffolds by voice and text when needed and includes a voice-based input mode. An evalua-tion with 182 learners in a 2 x 2 lab experiment demonstrated that Sara, compared to more traditional conversational agents, significantly improved learning in a programming task. This study highlights the importance of including scaf-folding and voice-based conversational agents in online videos to improve meaningful learning.
Towards Empowering Educators to Create their own Smart Personal Assistants. Winkler, Rainer; Söllner, Matthias. In Proceedings of the Hawaii International Conference on System Sciences (HICSS), S. 1–10. HICSS, 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Despite a growing body of research about the design and use of Smart Personal Assistants such as Amazon’s Alexa or Google’s Assistant, little is known about their ability to help educators offering individual support in large-scale learning environments. Smart Personal Assistant ecosystems empower educators to develop their own agents without deep technological knowledge. The objective of this paper is to design and validate a method that helps educators to create Smart Personal Assistants as learning tutors. Using a design science research approach, we first gather requirements from students and educators as well as from information systems and education theory. Next, we create an alpha version of our method and evaluate it with a focus group before we instantiate our artifact in an everyday learning environment. The findings indicate that our method is able to empower educators to design Smart Personal Assistants that significantly improve students’ learning success.
Improving Students? Problem-Solving Skills with Smart Personal Assistants. Winkler, Rainer; Söllner, Matthias; Leimeister, Jan Marco. In 80th Annual Meeting of the Academy of Management. Academy of Management, Vancouver, 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Tomorrow’s organizations need employees who are able to deal with rapid changes and solve non-routine problems. Gaining problem-solving skills is considered the number-one skill for future employees to succeed professionally. Predominant learning theories agree that the most effective way to gain these skills is for everyone to receive individual support by their own private tutor. For educational institutions such as high schools and universities, this is often not possible due to financial and organizational restrictions. A new emerging class of information technology – specifically Smart Personal Assistants (e.g., Google’s Assistant or Amazon’s Alexa) – has the potential to address this problem by interacting with students in a manner comparable to human tutors because of its high degree of adaptability, interactivity and accessibility. Even though there exists a growing body of research about the design and use of Smart Personal Assistants for learning, empirical evidence of their ability to help students improve their problem-solving skills is still scarce. Grounded on technology-mediated learning theory, this study uses a mixed-method approach consisting of two field quasi-experiments and one post-experiment focus group discussion at a business high school and a vocational business school with a total of 90 students to measure the effect of using Smart Personal Assistants on acquiring problem-solving skills. The empirical results show that students in the experiment classes acquired significantly more problem-solving skills than those in the control group mainly explained by changes in their learning process. The findings provide empirical evidence for the importance of using new emerging Smart Personal Assistants on general skill development, and specifically on problem-solving skill development. Moreover, our work can guide educational institutions and educators in designing and implementing Smart Personal Assistants in their own learning environments.
Using Smart Personal Assistants for Online Learning Activities: What benefits can we expect?. Winkler, Rainer; Weingart, Pablo; Söllner, Matthias; and. In 15th International Conference on Wirtschaftsinformatik (WI), S. 465–479. 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
With the increasing popularity of massive open online courses, universities are able to reach a wider audience without restriction and for comparably low costs. However, in these learning environments, educators are hardly able to offer individual support to their learners. According to learning theory, the lack of individual support in online learning environments can considerably limit learning success. In our paper, we argue that new emerging Smart Personal Assistants (SPAs) have the capabilities to address this problem by building up an interaction with the learner similar to a human tutor. Drawing on the concept of the Interactive, Constructive, Active and Passive (ICAP) Framework, we designed an experiment with 76 participants, where one group received text-based learning materials and the other group received additional scaffolds from an interactive, text-based smart personal assistant. Posttest-score comparisons revealed that learners interacting with the SPA were able to achieve higher learning outcomes.
A Review of the Empirical Literature on Conversational Agents and Future Research Directions. Zierau, Naim; Elshan, Edona; Visini, Camillo; Janson, Andreas. In International Conference on Information Systems (ICIS). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The knowledge base related to user interaction with conversational agents (CAs) has grown dramatically but remains segregated. In this paper, we conduct a systematic literature review to investigate user interaction with CAs. We examined 107 papers published in outlets related to IS and HCI research. Then, we coded for design elements and user interaction outcomes, and isolated 7 significant determinants of these outcomes, as well as 42 themes with inconsistent evidence, providing grounds for future research. Building upon the insights from the analysis, we propose a research agenda to guide future research surrounding user interaction with CAs. Ultimately, we aim to contribute to the body of knowledge of IS and HCI in general and user interaction with CA in particular by indicating how developed a research field is regarding the number and content of the respective contributions. Furthermore, practitioners benefit from a structured overview related to CA design effects.
Trust in Smart Personal Assistants: A Systematic Literature Review and Development of a Research Agenda. Zierau, Naim; Engel, Christian; Söllner, Matthias; Leimeister, Jan Marco. In 15th International Conference on Wirtschaftsinformatik (WI), S. 99–114. 2020.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Smart Personal Assistants (SPA) fundamentally influence the way individuals perform tasks, use services and interact with organizations. They thus bear an immense economic and societal potential. However, a lack of trust - rooted in perceptions of uncertainty and risk - when interacting with intelligent computer agents can inhibit their adoption. In this paper, we conduct a systematic literature review to investigate the state of knowledge on trust in SPAs. Based on a concept-centric analysis of 50 papers, we derive three distinct research perspectives that constitute this nascent field: user interface-driven, interaction-driven, and explanation-driven trust in SPAs. Building on the results of our analysis, we develop a research agenda to spark and guide future research surrounding trust in SPAs. Ultimately, this paper intends to contribute to the body of knowledge of trust in artificial intelligence-based systems, specifically SPAs. It does so by proposing a novel framework mapping out their relationship.
Towards Developing Trust-Supporting Design Features for AI-Based Chatbots in Customer Service. Zierau, Naim; Hausch, Michael; Bruhin, Olivia; Söllner, Matthias. In International Conference on Information Systems (ICIS). 2020.
- [ Abstract ]
- [ BibSonomy-Post ]
Chatbots are predicted to play a key role in customer service based on recent advances in the area of Artificial Intelligence (AI). However, a lack of user trust impedes the widespread adaption of AI-based chatbots. Still, there is a lack of systematically derived design knowledge concerning user trust in those agents. In this short paper, we report on the first steps of our design science research project on which design principles are relevant for building trust in chatbots. Based on trust literature and user interviews, we propose preliminary requirements and design principles for trust-enhancing design features for chatbots in customer service. Furthermore, we present a first instantiation of those principles. These insights will support researchers and practitioners to better understand how user trust in chatbots can be systematically built to increase adoption and usage.
The Anatomy of User Experience with Conversational Agents: A Taxonomy and Propositions of Service Clues. Zierau, Naim; Wambsganss, Thiemo; Janson, Andreas; Schöbel, Sofia; Leimeister, Jan Marco. In International Conference on Information Systems (ICIS). 2020.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Conversational agents (CAs) represent a paradigm shift in regards to how humans use information systems. Although CAs have recently attracted considerable research interest, there is still limited shared knowledge about the distinctive characteristics of CAs from a user experience-based perspective. To address this gap, we conducted a systematic literature review to identify CA characteristics from existing research. Building on classifications from service experience theory, we develop a taxonomy that classifies CA characteristics into three major categories (i.e. functional, mechanic, humanic clues). Subsequently, we evaluate the usefulness of the taxonomy by interviewing six domain experts. Based on this categorization and the reviewed literature, we derive three propositions that link these categories to specific user experience dimensions. Our results support researchers and practitioners by providing deeper insights into service design with CAs and support them in systematizing and synthesizing research on the effects of specific CA characteristics from a user experience-based perspective.

2019[ to top ]

The Impact of Private and Work-related Smartphone Usage on Interruptibility. Anderson, Christoph; Heinisch, Judith S.; Ohly, Sandra; David, Klaus; Pejovic, Veljko. In Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, von UbiComp/ISWC ’19 Adjunct, S. 1058–1063. ACM, London, United Kingdom, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
In the last decade, the effects of interruptions through mobile notifications have been extensively researched in the field of Human-Computer Interaction. Breakpoints in tasks and activities, cognitive load, and personality traits have all been shown to correlate with individuals' interruptibility. However, concepts that explain interruptibility in a broader sense are needed to provide a holistic understanding of its characteristics. In this paper, we build upon the theory of social roles to conceptualize and investigate the correlation between individuals' private and work-related smartphone usage and their interruptibility. Through our preliminary study with four participants over 11 weeks, we found that application sequences on smartphones correlate with individuals' private and work roles. We observed that participants engaged in these roles tend to follow specific interruptibility strategies - integrating, combining, or segmenting private and work-related engagements. Understanding these strategies breaks new ground for attention and interruption management systems in ubiquitous computing.
Towards an Integrative Understanding of Privacy Nudging – Systematic Review and Research Agenda. Barev, Torben Jan; Janson, Andreas. In Annual Pre-ICIS Workshop on HCI Research in MIS (Pre-ICIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
When using digital technologies, various data traces are left behind for collection, storage and analysis. Innovative solutions for information systems are needed that mitigate privacy risks and foster information privacy. One mechanism to achieve this are privacy nudges. Nudges are a concept from behavioural economics to influence individual’s decisions. This paper focusses on building an integrative understanding of privacy nudging. Specifically, we conceptualize the constituting characteristics of privacy nudges by conducting a systematic literature review to cover the current state of knowledge in the interdisciplinary privacy nudge literature stream. We structure the intrapersonal factors that determine effectiveness for each privacy nudge in a morphological box and conceptualize on this basis current research coverage as well as demand for future research. Finally, we develop theoretical propositions contributing to the discussion of how to study and design effective privacy nudges that can pave the way for more privacy sensitive IT systems.
CHARIOT - Towards a Continuous High-Level Adaptive Runtime Integration Testbed. Barnes, C. M.; Bellman, K.; Botev, J.; Diaconescu, A.; Esterle, L.; Gruhl, C.; Landauer, C.; Lewis, P. R.; Nelson, P. R.; Stein, A.; Stewart, C.; Tomforde, S. In 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W), S. 52–55. IEEE, 2019.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Self-Improving System Integration -- On a Definition and Characteristics of the Challenge. Bellman, K. L.; Gruhl, C.; Landauer, C.; Tomforde, S. In 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W), S. 1–3. 2019.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
The self-improving system integration (SISSY) initiative-sometimes also called self-integration-started over six years ago. Recently, we have seen contributions approaching parts of the scope from different directions. In order to provide a better understanding how these attempts support the development of novel SISSY technology, this paper presents a definition of the term. In addition, it discusses the fundamental challenges stemming from the increasingly interconnected character of large-scale distributed and adaptive systems typically referred to as "Interwoven Systems", with these systems describing the basic motivation for SISSY research.
Positioning of Active Wheels for Optimal Ball Handling. Beuermann, Maximilian; Ossenkopf, Marie; Geihs, Kurt. In Robot World Cup, S. 30–43. Springer, 2019.
- [ BibSonomy-Post ]
Yes, We Can! Blockchain Based Crowdfunding and Crowdworking. Billert, Matthias. In Pre-ICIS SIGBPS Workshop on Blockchain and Smart Contract (Pre-ICIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In the current process of crowdfunding and crowdworking, many criteria-based conditions must be considered on different platforms. Assignments must be initiated for each platform, which costs time, money and resources. In order to counteract these challenges and reduce transactions, we developed a blockchain-based platform using a design-oriented approach. This platform accompanies the process from requirements to self-executing, event- and condition-controlled contracts in a partially automated manner. Based on the literature of crowdfunding, crowdworking and blockchain-based smart contracts, we derived requirements for a platform creation. While we contribute to the literature by eliciting design-oriented requirements, we show practical implications by building a blockchain-based platform concept for facilitating a more efficient combined crowdfunding and crowdworking process by reducing transactions.
Where is the Bot in our Team? Toward a Taxonomy of Design Option Combinations for Conversational Agents in Collaborative Work. Bittner, Eva A. C.; Oeste-Reiß, Sarah; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
With rapid progress in machine learning, language technologies and artificial intelligence, conversational agents (CAs) gain rising attention in research and prac-tice as potential non-human teammates, facilitators or experts in collaborative work. However, designers of CAs in collaboration still struggle with a lack of com-prehensive understanding of the vast variety of design options in the dynamic field. We address this gap with a taxonomy to help researchers and designers understand the design space and the interrelations of different design options and recognize useful design option com-binations for their CAs. We present the iterative deve-lopment of a taxonomy for the design of CAs grounded in state of the art literature and validated with domain experts. We identify recurring design option combina-tions and white spots from the classified objects that will inform further research and development efforts.
Experimentalismus in der Soziologie. Forschungsprogramm und Brückenschläge. Bogusz, Tanja; Lamla, Jörn. In Komplexe Dynamiken globaler und lokaler Entwicklungen. Verhandlungen des 39. Kongresses der Deutschen Gesellschaft für Soziologie in Göttingen 2018, N. Burzan (Hrsg.). 2019.
- [ URL ]
- [ BibSonomy-Post ]
Early Pedestrian Movement Detection Using Smart Devices Based on Human Activity Recognition. Botache, Diego; Dandan, Liu; Bieshaar, Maarten; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), C. Draude, M. Lange, B. Sick (Hrsg.), S. 229–238. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ DOI ]
- [ BibSonomy-Post ]
On Learning in Collective Self-Adaptive Systems: State of Practice and a 3D Framework. D’Angelo, M.; Gerasimou, S.; Ghahremani, S.; Grohmann, J.; Nunes, I.; Pournaras, E.; Tomforde, S. In 2019 IEEE/ACM 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), S. 13–24. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
The Future of Human-AI Collaboration: A Taxonomy of Design Knowledge for Hybrid Intelligence Systems. Dellermann, Dominik; Calma, Adrian; Lipusch, Nikolaus; Weber, Thorsten; Weigel, Sascha; Ebel, Philipp. In Hawaii International Conference on System Sciences (HICSS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recent technological advances, especially in the field of machine learning, provide astonishing progress on the road towards artificial general intelligence. However, tasks in current real-world business applications cannot yet be solved by machines alone. We, therefore, identify the need for developing socio-technological ensembles of humans and machines. Such systems possess the ability to accomplish complex goals by combining human and artificial intelligence to collectively achieve superior results and continuously improve by learning from each other. Thus, the need for structured design knowledge for those systems arises. Following a taxonomy development method, this article provides three main contributions: First, we present a structured overview of interdisciplinary research on the role of humans in the machine learning pipeline. Second, we envision hybrid intelligence systems and conceptualize the relevant dimensions for system design for the first time. Finally, we offer useful guidance for system developers during the implementation of such applications.
DimDraw - A Novel Tool for Drawing Concept Lattices. Dürrschnabel, Dominik; Hanika, Tom; Stumme, Gerd. In ICFCA (Supplements), Bd. 2378 von CEUR Workshop Proceedings, D. Cristea, F. L. Ber, R. Missaoui, L. Kwuida, B. Sertkaya (Hrsg.), S. 60–64. CEUR-WS.org, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Internal Crowd Work as a Source of Empowerment - An Empirical Analysis of the Perception of Employees in a Crowdtesting Project. Durward, David; Simmert, Benedikt; Blohm, Ivo; Peters, Christoph. In International Conference on Wirtschaftsinformatik (WI). Siegen, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Internal crowd work has emerged as a new form of digital gainful employment that changes the nature of work. However, the possible effects of internal crowd work on the individual level have been largely neglected. In this paper, we therefore present our research in progress which is concerned with the effects of work characteristics in internal crowd work that have impact on the individual’s empowerment and satisfaction. Thus, we developed our research model and conducted an online survey amongst 118 internal crowd workers of a Swiss bank who were asked to test new software. Our expected contribution will increase the understanding of internal crowd work and provide important insights for organizations to (re-) design work on internal IT-platforms.
How to Empower the Workforce – Analyzing Internal Crowd Work as a Neo-Socio-Technical System. Durward, David; Simmert, Benedikt; Peters, Christoph; Blohm, Ivo; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2019.
- [ URL ]
- [ BibSonomy-Post ]
Formal Context Generation Using Dirichlet Distributions. Felde, Maximilian; Hanika, Tom. In ICCS, Bd. 11530 von Lecture Notes in Computer Science, D. Endres, M. Alam, D. Sotropa (Hrsg.), S. 57–71. Springer, 2019.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Towards a Taxonomy of Text Mining Features. Fromm, Hansjörg; Wambsganss, Thiemo; Söllner, Matthias. In European Conference on Information Systems (ECIS) 2019, J. vom Brocke, S. Gregor, O. Müller (Hrsg.), S. 12. European Conference on Information Systems (ECIS), 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Recently, text mining has received special attention from both researchers and practitioners, since it enables the development of intelligent and automated services. Text mining has been influenced by different disciplines like computer science, statistics, computational linguistics and library and infor-mation sciences. However, text mining features that evolved in one particular discipline are often un-known or rarely used in the other disciplines. No scientific feature framework exits which facilitates costly feature engineering and evaluation. Therefore, we aim to develop a novel text mining feature taxonomy, which helps researchers and practitioners to develop, refine, compare and evaluate their text mining studies. In this research in progress paper, we focus on laying the foundation for our tax-onomy development by presenting our first two research cycles. Here, we were aiming for diversity, not completeness. We derived five dimensions and classified different text features accordingly to pro-vide a deeper understanding.
Umsetzung einer 3D-360°-Lerneinheit in der praktischen Ausbildung von Handwerkern: Einsatzmöglichkeiten von interaktiven immersiven Medien. Funk, J.; Klingauf, A.; Lüüs, A.; Schmidt, L. In Proceedings of DELFI Workshops (Berlin 2019), S. Schulz (Hrsg.), S. 161–172. Gesellschaft für Informatik e. V, Bonn, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Im Folgenden wird die Umsetzung einer Lerneinheit in der praktischen Ausbildung von Handwerker*innen mithilfe von interaktiven 3D-360°-Videos vorgestellt. Vorhandene Inhalte aus dem Projekt FAINLAB wurden dabei als interaktive immersive Anwendung für das Erlernen der Herstellung eines Fliesenspiegels umgesetzt. Die Anwendung kann mithilfe eines Smartphone-basierten Head-Mounted Displays (HMD) genutzt werden und ermöglicht durch niedrige Kosten eine breite Verwendung in der Ausbildung. Die Interaktion wird mittels mehrerer Schaltflächen ermöglicht, die per Blicksteuerung zu nutzen sind, wie eine formative Evaluation mit Studierenden absicherte. Es wird auf eine vergleichende Evaluation verwiesen, die zeigt, dass die Anwendung gegenüber dem ursprünglichen FAINLAB-Video bei gleichem Lernerfolg eine höhere Motivation der Lernenden bewirkt.
More Than a Need for Knowledge: Understanding Drivers for Knowledge Seeking and Knowledge Sharing Behavior in Online Communities. Gerken, Maike; Bretschneider, Ulrich; Hülsbeck, Marcel. In International Conference on Information Systems (ICIS). Munich, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Knowledge seeking is the default activity in online communities and therefore important for their functioning. Existing research studies on why members seek knowledge overlook other factors than a simple need for knowledge, resulting in an extremely narrow body of knowledge. We propose that a need for advice can increase knowledge seeking and is further shaped by perceptions of reciprocity, self-esteem, and identification with the community. By surveying 186 respondents from 34 large online communities and applying OLS regression analyses, we find that knowledge seeking is driven by need for advice and identification, but not reciprocity. The results further show that members with high self-esteem seek less knowledge. Yet, the decision to seek knowledge depends on the level of self-esteem and this is predicted by need for advice. Our results contribute to the currently sparse body on knowledge seeking and add to the realization of necessary design attributes of online communities.
COOP - AutomatiC ValidatiOn of EvOlving Microservice ComPositions. Groh, Olga; Baraki, Harun; Jahl, Alexander; Geihs, Kurt. In Proceedings of the Seminar Series on Advanced Techniques & Tools for Software Evolution (SATTOSE 2019). 2019.
- [ BibSonomy-Post ]
Conexp-Clj - A Research Tool for FCA. Hanika, Tom; Hirth, Johannes. In ICFCA (Supplements), Bd. 2378 von CEUR Workshop Proceedings, D. Cristea, F. L. Ber, R. Missaoui, L. Kwuida, B. Sertkaya (Hrsg.), S. 70–75. CEUR-WS.org, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Relevant Attributes in Formal Contexts. Hanika, Tom; Koyda, Maren; Stumme, Gerd. In ICCS, Bd. 11530 von Lecture Notes in Computer Science, D. Endres, M. Alam, D. Sotropa (Hrsg.), S. 102–116. Springer, 2019.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Discovering Implicational Knowledge in Wikidata. Hanika, Tom; Marx, Maximilian; Stumme, Gerd. In ICFCA, Bd. 11511 von Lecture Notes in Computer Science, D. Cristea, F. L. Ber, B. Sertkaya (Hrsg.), S. 315–323. Springer, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Pilotstudie zur Roboterunterstützung des Menschen bei manueller Montage. Hegenberg, J.; Schimpf, D. W.; Fischer, N.; Schmidt, L. In Arbeit interdisziplinär analysieren - bewerten - gestalten: 65. Kongress der Gesellschaft für Arbeitswissenschaft (Dresden 2019), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.9.1). GfA-Press, Dortmund, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In diesem Beitrag wird ein Konzept zur Integration einer kollaborativen Roboterunterstützung an einem manuellen Montagearbeitsplatz vorgestellt. Dazu wurde exemplarisch ein Arbeitsplatz in der Wellenvormontage der Getriebefertigung in der Automobilindustrie betrachtet. Die Arbeitsprozesse bei der manuellen Montage wurden analysiert und das darauf basierende Konzept in einem vollfunktionsfähigen Mock-up umgesetzt, welcher die Montage ohne und mit Roboterunterstützung ermöglicht. Auf Basis dieses Mock-ups wurde eine Nutzerstudie (n = 8) durchgeführt, die die Ergonomie und Gebrauchstauglichkeit des Konzepts sowie das wirtschaftliche Potenzial der Roboterunterstützung evaluiert.
Towards Corner Case Identification in Cyclists’ Trajectories. Heidecker, F.; Bieshaar, M.; Sick, B. In Proceedings of CSCS ’19: 3rd ACM Symposium on Computer Science in Cars (CSCS ’19). 2019.
- [ BibSonomy-Post ]
Angry or Climbing Stairs? Towards Physiological Emotion Recognition in the Wild. Heinisch, J. S.; Anderson, C.; David, K. In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), S. 486–491. IEEE, Kyoto, Japan, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Physiological responses to emotions play a vital role in the field of emotion recognition. Machine-learning models implemented in wristbands or wearables, already exploit unique patterns in physiological responses to provide information about humans emotional states. However, such responses are commonly interfered and overlapped by physical activities, posing a challenge for emotion recognition “in-the-wild”. In this paper, we address this challenge by investigating new features based on the linear regression line and machine-learning models for emotion recognition. We triggered emotions through audio samples and recorded physiological responses from 18 participants before and while performing physical activities. We trained models with the least strenuous physical activity (sitting) and tested with the remaining, more strenuous ones. For three different emotion categories, we achieved classification accuracies up to 67%. Considering individual activities and participants, we achieve up to 73% classification accuracy, indicating the viability of emotion recognition models and features non-sensitive to interferences caused by physical activities.
Die parlamentarische Kontrolle digitaler Räume. Hornung, Gerrit. In Bitburger Gespräche. Jahrbuch 2018, S. G. für Rechtspolitik, I. für R. der U. Trier (Hrsg.), S. 95–112. C.H.Beck, Munich, Germany, 2019.
- [ BibSonomy-Post ]
The Emergency Responsive Digital City, Proceedings of the World Congress on Resilience, Reliability and Asset Management. Hornung, Gerrit; Hollick, M. In Proceedings of the World Congress on Resilience, Reliability and Asset Management, S. 136–139. 2019.
- [ BibSonomy-Post ]
Designing for Social Presence and Leveraging the Outcomes of Customer Service Chatbots. Janson, Andreas; Degen, Oliver; Schwede, Melanie. In Academy of Management Annual Meeting (AOM). Boston, Massachusetts, USA, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Chatbots are innovative text-based dialogue systems that are oftentimes used in digital customer service encounters, since chatbots offer a lot of potential to optimize the relationship with the customer. However, chatbots face various problems, such as low adoption and satisfaction rates as well as other negative reactions from the customer. Companies therefore need to consider different design features when developing their chatbots. Key for designing chatbots is the use of anthropomorphic design elements. In this study, we examine the two anthropomorphic design elements of personification, which includes a human like appearance of the chatbot, and socially oriented communication, which means a more sensitive and extensive communication behavior. We tested the influence of the two design elements on social presence, satisfaction, trusting beliefs and empathy. The results of our experiment support a significant influence of the two anthropomorphic design elements on social presence. In addition, our findings show the central role of social presence concerning chatbot perceptions. First, social presence has a strong direct influence on trusting beliefs, empathy and satisfaction. Second, social presence acts as a mediator for both anthropomorphic design elements on satisfaction with a chatbot. The derived implications provide a theory for understanding anthropomorphic design elements related to chatbots and we offer design principles for practitioners that enable more effective chatbot implementations.
Wirkung von interaktiven 3D-360°-Lernvideos in der praktischen Ausbildung von Handwerkern. Klingauf, A.; Funk, J.; Lüüs, A.; Schmidt, L. In DELFI 2019: 17. Fachtagung Bildungstechnologien (Berlin 2019), von Lecture Notes in Informatics (LNI) - Proceedings, N. Pinkwart, J. Konert (Hrsg.), S. 145–156. Gesellschaft für Informatik, Bonn, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die vorliegende Studie vergleicht den Einsatz von 3D-360°\hbox{-}}Lernvideos mit konventionellen Lernvideos bei der praktischen Ausbildung von Handwerkern. Es wurde die Hypothese geprüft, dass Motivation und Ablenkung durch die Technologie einen gegensätzlichen Einfluss auf den Lernerfolg haben und so die vorliegenden gemischten Befunde in diesem Feld erklären. Insgesamt 20 Auszubildende des ersten Lehrjahrs der Ausbildung zum Hoch- bzw. Tiefbaufacharbeiter lernten entweder mit konventionellen Lernvideos am Laptop oder mit 3D\hbox{-}}360°-Videos, die auf einem Smartphone\hbox{-}}basierten Head-Mounted Display angeschaut wurden. Der Lernerfolg wurde anhand einer praktischen Aufgabe gemessen, die von zwei unabhängigen Ratern bewertet wurde. Die durch die Lernmethode ausgelöste Motivation und Ablenkung der Lernenden wurde mithilfe von Fragebögen gemessen. Wie erwartet zeigte sich in der Gruppe der mit 3D\hbox{-}}360°\hbox{-}}Videos Lernenden sowohl eine höhere Motivation als auch eine höhere Ablenkung als in der Kontrollgruppe. Der Lernerfolg unterschied sich nicht zwischen den Gruppen. Die erwarteten Korrelationsmuster zur Unterstützung der weiteren Teilhypothesen konnten nicht gefunden werden.
Nutzeranforderungen an ein Assistenzsystem für den ÖPNV. Klingauf, A.; Hegenberg, J.; Lambrecht, F.; Bieland, D.; Schmidt, L.; Sommer, C. In Arbeit interdisziplinär analysieren - bewerten - gestalten: 65. Kongress der Gesellschaft für Arbeitswissenschaft (Dresden 2019), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.2.6). GfA-Press, Dortmund, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Um die Attraktivität des öffentlichen Nahverkehrs zu erhöhen, wurde ein Mobilitätsassistenzsystem (MAS) konzipiert, das die Nutzer_innen in den Bereichen Anschlusssicherung und Belegungszustand sowie durch einen integrierten Lieferdienst unterstützt. Dazu wurde eine Anforderungserhebung mit Experten (n = 5) und Nutzer_innen (n = 426) durchgeführt, womit auch die Anforderungen von älteren Menschen und Menschen mit Einschränkungen besonders berücksichtigt werden sollten. Entgegen der Erwartungen ist das MAS für diese Gruppen nicht attraktiver als für andere Nutzer_innen. Die meisten Nutzer_innen wünschen sich die Interaktion mittels einer App, ältere Menschen und Menschen mit Einschränkungen bevorzugen andere Schnittstellen.
Text Presentation for Augmented Reality Applications in Dual-Task Situations. Klose, E. M.; Mack, N. A.; Hegenberg, J.; Schmidt, L. In 26th IEEE Conference on Virtual Reality and 3D User Interfaces (Osaka 2019), R. Teather, Y. Itoh, J. Gabbard, F. Argelaguet, A.-H. Olivier, D. Keefe (Hrsg.), S. 636–644. IEEE, Piscataway, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
We investigate how reading text in augmented reality (AR) glasses and the simultaneous execution of three real-world tasks interfere with each other. The three tasks are a visual stimulus-response task (VSRT), a simple walking task and a walking obstacle course. Also, we investigate the effects of different AR text positions on primary task and reading performance as well as subjective preference. We propose a novel out of sight body-locked text placement for AR text presentation to be used in dual-task situations and compare it to head-locked text placement, each in two heights. AR reading affected performance in all tasks and reading speed was affected in all dual-task conditions. Participants subjectively preferred the body-locked text presentation, while objective measures do not reflect that preference. Differences between the tasks and several interaction effects between task and AR text placement demonstrate the necessity to carefully consider the context of use when designing AR reading UIs. The presented study with 12 participants provides insights into the effects of AR glasses usage in dual-task situations and several design recommendations are derived from the results.
Mit benutzerzentrierter Entwicklung zur Integration von sozialen Aspekten in die Projektarbeit. Klose, E. M.; Ni, I.; Schmidt, L. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik - Informatik für Gesellschaft (Workshop-Beiträge), von Lecture Notes in Informatics, C. Draude, M. Lange, B. Sick (Hrsg.), S. 447–463. Gesellschaft für Informatik e. V, Bonn, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Ein benutzerzentrierter Entwicklungsansatz kann in Technologieentwicklungsprojekten dazu genutzt werden, um nachhaltige, sozial verantwortliche Gestaltungslösungen zu fördern. Dieser Ansatz rückt den Menschen und seine Aufgaben in den Fokus der technischen Systementwicklung und bezieht Benutzer sowie weitere Beteiligte von Anfang an fortlaufend in den Entwicklungsprozess ein. So wird sichergestellt, dass die entwickelten Systeme, Dienstleistungen und Produkte eine hohe Gebrauchstauglichkeit und Akzeptanz aufweisen und dass auch langfristige Folgen der Nutzung betrachtet werden. Dieser Beitrag gibt einen Überblick über das methodische Vorgehen mit diesem Ansatz und beschreibt am Beispiel eines mehrjährigen Verbundforschungsprojektes die konkrete praktische Anwendung mit exemplarischen Methoden.
Towards Solving the Personalization-Privacy Paradox for Smart Personal Assistants. Knote, Robin. In Hawaii International Conference on System Sciences (HICSS). 2019.
- [ URL ]
- [ BibSonomy-Post ]
Towards Smart Assistance Systems for Physical and Manual Tasks. Knote, Robin. In European Conference on Information Systems (ECIS). Stockholm, Sweden, 2019.
- [ Abstract ]
- [ BibSonomy-Post ]
Although automation of physical work is continuously accelerated by advances in information technol-ogy, many complex tasks, such as in manufacturing, assembly or maintenance still require human work. In this context, Smart Physical and Manual Task Assistance Systems (SPMTAs) support workers by adapting to their current situation or task. Since the importance of physical work is still evident in a digitized economy, there is a need for properly designed SPMTAs in order to increase job satisfaction and performance of workers by taking off physical and cognitive strain. However, scientific literature on how to design SPMTAs is sparse. Combining sociotechnical systems and work design theory, we derived propositions and conducted interviews with workers of a German car component manufacturer as part of a design science project. The company uses three SPMTAs for assembly, final inspection, and tool management. As a result, we elicited 18 design requirements for SPMTAs to increase job satisfac-tion and performance. In this research-in-progress paper, we present our preliminary results and dis-cuss next steps.
Classifying Smart Personal Assistants: An Empirical Cluster Analysis. Knote, Robin; Janson, Andreas; Söllner, Matthias; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Gestaltung smarter persönlicher Assistenten zwischen Rechtsverträglichkeit und Dienstleistungsqualität: Gestaltungsziele und Zielkonflikte. Knote, Robin; Thies, Laura Friederike; Söllner, Matthias; Roßnagel, Alexander; Leimeister, Jan Marco. In INFORMATIK 2019, Bd. Lecture Notes in Informatics (LNI) - Proceedings: Series of the Gesellschaft für Informatik (GI), K. David, K. Geihs, M. Lange, G. Stumme (Hrsg.), S. 435–448. Gesellschaft für Informatik (GI), Bonn, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Smarte persönliche Assistenten von Amazon, Google und zahlreichen anderen Anbietern ermöglichen es, qualitativ hochwertige elektronische Dienstleistungen anzubieten. Gleichzeitig bringen diese Systeme auch viele Risiken mit sich. Berichte von diskriminierenden oder unverständlichem Systemverhalten häufen sich und verursachen Skepsis in der Gesellschaft. Diesen Problemen kann mit einer gleichermaßen rechtsverträglichen und qualitätsorientierten IT-Gestaltung entgegengewirkt werden. In diesem Beitrag werden Rechtsverträglichkeit und Dienstleistungsqualität als elementare Ziele für die Gestaltung smarter persönlicher Assistenten eingeführt. Zudem werden Zielkonflikte wie die Personalisierung von Leistungen bei gleichzeitiger Datensparsamkeit diskutiert und Implikationen für die Systemgestaltung erläutert.
Using grid supporting flexibility in electricity distribution networks. König, Immanuel; Heilmann, Erik; Henze, Janosch; David, Klaus; Wetzel, Heike; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft, Bd. P-294 von LNI, K. David, K. Geihs, M. Lange, G. Stumme (Hrsg.), S. 531–544. Gesellschaft für Informatik e.V., Kassel, Germany, 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Pose Based Start Intention Detection of Cyclists. Kress, V.; Jung, J.; Zernetsch, S.; Doll, K.; Sick, B. In 2019 IEEE Intelligent Transportation Systems Conference (ITSC), S. 2381–2386. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Pose Based Trajectory Forecast of Vulnerable Road Users. Kress, V.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI), S. 1200–1207. Xiamen, 2019.
- [ BibSonomy-Post ]
Start Intention Detection of Cyclists using an LSTM Network. Kress, Viktor; Jung, Janis; Zernetsch, Stefan; Doll, Konrad; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), Bd. P-295, C. Draude, M. Lange, B. Sick (Hrsg.), S. 219–228. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Gestaltung hybrider Entscheidungsarchitekturen zur Förderung kritischer Verbraucherkompetenzen. Kropf, Jonathan; Lamla, Jörn; Leimeister, Jan Marco; Oeste-Reiß, Sarah; Weber, Thorsten. In Internationale Tagung Wirtschaftsinformatik (WI), Bd. 14. Siegen, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Internetanwendungen, Soziale Medien, wirkmächtige KI-Algorithmen und Active‐Learning‐Technologien bilden heute bereits hybride Entscheidungsarchitekturen. Gemeint sind damit die oft unbemerkten Rahmungen innerhalb derer (Verbraucher-)Entscheidungen getroffen werden und die sich auf hybride Verbindungen von künstlicher und menschlicher Intelligenz verteilen. Die Gestalter solcher Architekturen werden dabei mit einer großen Machtfülle ausgestattet, deren Konsequenzen gegenwärtig nur schwer absehbar sind. Daraus ergibt sich für die Forschung die Frage, wie hybride Entscheidungsarchitekturen gesellschaftlich-wünschenswert gestaltet sein sollten, damit sie die kritischen Kompetenzen der Verbraucher erhalten und fördern, anstatt sie unbemerkt zu untergraben. Wir schlagen dafür ein hybrides Entscheidungsunterstützungssystem vor, das durch Erkenntnisse aus den Literaturbereichen der Rechtfertigungsordnungen, Mapping of Controversies sowie auf pädagogischen Aspekten zur Kompetenzförderung aufbaut. Methodisch folgen wir einem gestaltungsorientierten Vorgehen, dem sog. Design Science Approach.
The Organic Computing Doctoral Dissertation Colloquium: Status and Overview in 2019. Krupitzer, Christian; Tomforde, Sven. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), Bd. P-295, C. Draude, M. Lange, B. Sick (Hrsg.), S. 545–554. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Multi-objective Optimisation in Hybrid Collaborating Adaptive Systems. Lesch, V.; Krupitzer, C.; Tomforde, S. In ARCS Workshop 2019; 32nd International Conference on Architecture of Computing Systems, S. 1–8. 2019.
- [ BibSonomy-Post ]
Emerging Self-Integration through Coordination of Autonomous Adaptive Systems. Lesch, V.; Krupitzer, C.; Tomforde, S. In 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W), S. 6–9. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Take the Wheel - Technology-driven Change in the Energy Sector. Li, Mahei Manhai; Müller, Jennifer; Ernst, Sissy-Josefina; Peters, Christoph. In International Conference on Information Systems (ICIS). 2019.
- [ URL ]
- [ BibSonomy-Post ]
From Service Systems Engineering to Service Innovation - A Modeling Approach. Li, Mahei Manhai; Peters, Christoph. In European Conference on Information Systems (ECIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Due to the advent of digitization, service innovation has become even more important for both business and service research alike. Current service systems engineering approaches have employed a recombinant perspective that follows innovation mechanisms to leverage existing company resources for new service innovations. Employing these innovation mechanisms is still challenging, since there is little support on how to structure and identify these mechanisms. We propose a model-based service system engineering approach to structure existing resources into one formal model, enabling the formalization of service innovation mechanisms. The formalized service innovation mechanisms allow for a graphical illustration and enable future research to apply functions to analyze how innovation impacts entire or specific parts of service systems. Furthermore, the mathematical model enables an object-oriented value-driven perspective on service systems and is basis for graphical software tools. We contribute to literature by formalizing service innovations and its mechanisms in the context of service systems and by combining concepts of service innovation and service systems engineering. We do so by a) formalizing service innovation mechanisms and b) demonstrating the application of formal service innovations along one specific software implementation case. For practice, the service system model can with simulating the effects of service innovations.
Developing a Production Structure Model using Service-Dominant Logic – A hypergraph-based Modeling Approach. Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In INFORMS International Conference on Service Science (ICSS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
To make a fundamental shift towards value orientation, manufacturing companies strategically move to integrate services into their portfolio. While manufacturing firms rely on production information systems as the backbone of their operations, these systems are based on product structure models (e.g., bill of materials). This poses a problem because services do not adhere to the goods-dominant perspective of product structures. To solve this divide, this paper proposes an integrative mathematical model for both production systems and service systems. This model draws upon concepts of service-dominant logic and is based on hypergraph theory. To illustrate that the production structure model includes both product structures and process structures, we further demonstrate that the production structure model can be transformed into either. Therefore, our theoretical contribution lies in introducing a structural model for production systems that is compatible with structures of a service system model. For practice, this model enables the development of production information systems that can plan and control products, services and hybrids.
Linking Strategy and Operations using a Service Business Model – a hypergraph theory-based approach. Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In International Research Symposium on Advancing Service Research and Practice (QUIS). Karlstad, Sweden, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Business models (BM) have become increasingly important and versatile abstract tools to describe businesses on both, a strategic, as well as operational level (Wirtz et al. 2015). These BMs are used to understand what a business does to remain competitive, strategically (Johnson et al. 2008). Existing research (Johnson et al. 2008; Wirtz et al. 2015) identified the importance of BMs for the success of businesses. Also, practice revealed that financially successful companies ascertain twice the level of importance than less successful companies (IBM, 2007). A BM is a conceptual and structural implementation of a business strategy and the foundation of business processes (Osterwalder and Pigneur, 2002). BMs include a strategy, input factors, processes, with an underlying financial model to ensure the profitability. In recent years BMs have become synonymous with entire companies. Literature shows a heterogeneous abstraction of BMs, sometimes referring to BMs as business unit or products (Wirtz et al. 2015). Service systems literature shows similar structures, with service systems referring to exchanges on an individual level, among business units or entire ecosystems (Chandler and Lusch 2015). We propose that a service systems perspective can systematically model businesses and capture its inherent complexities (Peters et al. 2015). The service business model (SBM) includes (1) the value proposition, which is the firm’s offering to the customer; (2) the value creation and delivery mechanisms, reflecting the value chain; (3) value capture and analysis of the BM and its constituent elements to understand how the firm generates profit. Our model, thus, captures the holistic characteristic of BM, while retaining the detailed information on how the business is constructed. Businesses are confronted with a complex, digitalized world, in which important service innovations are continuously emerging, which need to be designed and linked to the BM of a company, thus addressing the strategy to execution gap (Kaplan and Norton 2009). Typical BM tools, such as the business model canvas (Osterwalder et al. 2005), only provide a descriptive framework for structuring businesses, missing the interrelations of its BM elements. This is important for operational decision makers, who implement new service innovations. In sum, without a SBM that relates the high level strategic information to the detailed operations perspective, BMs only reflect half the picture. Hence, we develop a hypergraph theory-based underlying model for businesses to understand how the business works both from a strategic perspective, as well as from a detailed operational perspective. Our SBM makes value creation visible, relying on a systems perspective linking multi-dimensional input factors with set of activities and actors and thus capturing value proposition, value creation and delivery and value capture mechanisms (Li & Peters 2018). Attached table shows an overview of our SBM, which relies on a formally model (Li et al. 2018). It represents a base structure of businesses and can be used for operational purposes too (e.g.: scheduling, planning and cost analyses) and thus enables a high level strategic perspective to be integrated into the operational perspective, bridging the gap between strategy and execution for successful businesses.
Evaluierung der sozialen Akzeptanz verschiedener Interaktionsarten für Augmented-Reality-Datenbrillen. Mack, N.; Schmidt, L. In Mensch und Computer 2019 - Workshopband (Hamburg 2019), F. Steinicke, K. Wolf (Hrsg.), S. 150–157. Gesellschaft für Informatik e. V, Bonn, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die soziale Akzeptanz ist neben der praktischen Akzeptanz ein wichtiger Bestandteil der Akzeptanz eines Systems durch die Nutzer. Es ist möglich, dass trotz hoher praktischer Akzeptanz ein System nicht genutzt wird, da dieses sozial nicht akzeptabel ist. Für Augmented-Reality-Datenbrillen (AR-Datenbrillen) wurden schon verschiedene Faktoren determiniert, welche die soziale Akzeptanz beeinflussen können, um zu vermeiden, dass diese von den Nutzern abgelehnt werden. Ein wichtiger Faktor, welcher die soziale Akzeptanz einer Datenbrille beeinflussen kann, ist die Interaktionsart. Es ist anzunehmen, dass die Verwendung unterschiedlicher Interaktionsarten in dem gleichen sozialen Kontext mit dem gleichen Gesamtsystem nicht in der gleichen sozialen Akzeptanz resultiert. Nachfolgend wird eine Studie mit 10 Probanden und 6 aktuell auf AR-Datenbrillen verwendeten Interaktionsarten durchgeführt, um deren soziale Akzeptanz in verschiedenen Orts- und Zuschauerkontexten vergleichend zu evaluieren. Die Studie zeigt, dass die Interaktionsarten, insbesondere diverse Arten der Sprachinteraktion, mit steigender Distanz der sozialen Beziehung zu dem Zuschauer in der Bewertung degradieren und, dass der Ort des voraussichtlichen Einsatzes der Interaktionsart berücksichtigt werden muss.
Automated Learning of Pedestrian Walking Speed Profiles for Improved Movement Prediction. Morold, Michel; Bachmann, Marek; Mathuseck, Lars; David, Klaus. In LNI, Bd. P-295 von LNI, C. Draude, M. Lange, B. Sick (Hrsg.). Gesellschaft für Informatik e.V., Kassel, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Every year, about 310,500 pedestrians still lose their lives in traffic accidents worldwide. Cooperative pedestrian collision avoidance represents a promising approach to reduce those accident numbers. This approach assumes that pedestrians are equipped with mobile devices to obtain and exchange their current movement information with nearby vehicles and use those to predict and prevent possible collisions. However, the ability to predict collisions between a pedestrian and a vehicle also depends on the assumptions about the pedestrian’s future behavior. One important aspect of those assumptions is a pedestrian’s individual walking pattern, like his common or maximum speed. Thus, learning and applying individual walking speed profiles of pedestrians to improve movement prediction may increase the accuracy of a collision detection algorithm and could, in turn, reduce the probability of missing or erroneously triggering an alarm. In this publication, we propose an approach to learn individual walking speed profiles of a pedestrian based on smartphone Global Navigation Satellite System (GNSS) data and evaluate the ability to predict collisions based on those profiles. Therefore, we first conducted experiments to estimate the error of walking speed obtained from smartphone GNSS. Second, using our Pedestrian Monitor application, we recorded real-world walking speed information from nine participants. Based on these data, we show that individually learned walking speed profiles are able to increase the accuracy of predicting an impending collision.
Managing Work Systems for Complex Work via Crowdworking Platforms - How to Orchestrate the Interplay of Crowds. Mrass, Volkmar; Peters, Christoph. In Hawaii International Conference on System Sciences (HICSS), S. 6347–6356. 2019.
- [ URL ]
- [ BibSonomy-Post ]
Managing Initial Coin Offerings: Towards a Taxonomy of ICO Processes. Nikolaus, Lipusch; Dominik, Dellermann; Philipp, Ebel. In Hawaii International Conference on System Sciences (HICSS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
07.01.2019-12.01.2019
Teaching Commonsense and Dynamic Knowledge to Service Robots. Opfer, Stephan; Jakob, Stefan; Geihs, Kurt. In 11th Conference on Social Robotics (ICSR2019). 2019.
- [ BibSonomy-Post ]
ALICA 2.0 - Domain-Independent Teamwork. Opfer, Stephan; Jakob, Stefan; Jahl, Alexander; Geihs, Kurt. In Proceedings of 42nd German Conference on Artificial Intelligence (KI2019). 2019.
- [ BibSonomy-Post ]
Long-Horizon Active SLAM system for multi-agent coordinated exploration. Ossenkopf, Marie; Castro, Gastón; Pessacg, Facundo; Geihs, Kurt; De Cristóforis, Pablo. In 2019 European Conference on Mobile Robots (ECMR), S. 1–6. IEEE, 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Not all Reviews are Equal - a Literature Review on Online Review Helpfulness. Rietsche, Roman; Frei, Daniel; Stoeckli, Emanuel; Söllner, Matthias. In European Conference on Information Systems (ECIS) 2019, J. vom Brocke, S. Gregor, O. Müller (Hrsg.). European Conference on Information Systems (ECIS), 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The amount of online reviews is growing significantly. Between 2014 and 2017 the number of reviews for TripAdvisor grew by 300% and for Yelp by 208%. However, not all online reviews are equally valuable. Some reviews are perceived to be more helpful or trustworthy then others. Hence, a plethora of scholars have investigated the role of online reviews and researched factors and characteristics determining its helpfulness. Nevertheless, mixed findings were found. Consequently, the purpose of our paper is to present a holistic and representative analysis of the literature on factors indicating the helpfulness of online reviews. In total, we analyzed 81 journal articles and inductively created a framework resulting in four dimensions: review-related factors, reviewer-related factors, reader related factors and environment-related factors. The results reveled that researchers mainly focused on factors of the first two dimensions and that the findings are inconsistent and need to be solved by future research.
Insights on Using IT-Based Peer Feedback to Practice the Students’ Providing Feedback Skill. Rietsche, Roman; Söllner, Matthias. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality. Sandrock, C.; Herde, M.; Calma, A.; Kottke, D.; Sick, B. In 2019 International Joint Conference on Neural Networks (IJCNN), S. 1–8. 2019.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Distances for WiFi Based Topological Indoor Mapping. Schäfermeier, Bastian; Hanika, Tom; Stumme, Gerd. In 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous), November 12--14, 2019, Houston, TX, USA. 2019.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover's Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario.
Distances for wifi based topological indoor mapping. Schaefermeier, Bastian; Hanika, Tom; Stumme, Gerd. In Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. ACM, 2019.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
A Multi-Stage Clustering Framework for Automotive Radar Data. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In ITSC, Bd. abs/1907.03511, S. 2060–2067. IEEE, 2019.
- [ URL ]
- [ BibSonomy-Post ]
Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In 2019 IEEE Intelligent Vehicles Symposium (IV), S. 642–649. IEEE, Paris, France, 2019.
- [ BibSonomy-Post ]
Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM), S. 5–9. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Polizei und Datenschutz. Vorgaben der neuen JI-RL für technische und organisatorische Maßnahmen zur Gewährleistung datenschutzkonformer polizeilicher Datenverarbeitung. Schindler, Stephan; Borell, A. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik - Informatik für Gesellschaft. Konferenzbeiträge der 49. Jahrestagung der Gesellschaft für Informatik, S. 393–406. Gesellschaft für Informatik (Gi), Bonn, 2019.
- [ BibSonomy-Post ]
Praktische Ansätze zur ELSI-Integration in Technologieprojekte. Schmidt, L.; Hornung, G.; Leimeister, J. M. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik - Informatik für Gesellschaft (Workshop-Beiträge), von Lecture Notes in Informatics, C. Draude, M. Lange, B. Sick (Hrsg.), S. 401–402. Gesellschaft für Informatik e. V, Bonn, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In Förderausschreibungen wird zunehmend gefordert, ethische, rechtliche und soziale Implikationen (ELSI) der Technikentwicklung nicht nur begleitend, sondern mit einem integrierten Forschungsansatz in Technologieprojekten zu berücksichtigen. Erfahrungen mit der praktischen Umsetzung in der Projektarbeit sollen in diesem Workshop ausgetauscht werden.
Users’ Game Design Element Preferences in Health Behavior Change Support Systems for Physical Activity: A Best-Worst-Scaling Approach. Schmidt-Kraeplin, Manuel; Thiebes, Scott; Schöbel, Sofia; Sunyaev, Ali. In International Conference on Information Systems (ICIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Over the last decades, physical inactivity has become one of the leading health risk factors in modern societies. To incentivize people to be more physically active, gamified health behavior change support systems (HBCSSs) are a promising approach. These systems often make use of gamification to keep their users engaged over a sustained period of time. However, despite its popularity, gamification often fails due to insufficient designs, which neglect users’ needs. Building on extant research that investigated users’ preferences in other gamification contexts, we conduct a survey among 447 potential users of HBCSSs for physical activity, using a best-worst-scaling approach. Our results indicate that users generally prefer the game design elements progress, goals, points, and levels, which is partially different from past research on preferred game design elements in other contexts. Thus, our research contributes to the understanding of contextual differences in users’ gamification preferences.
Gamification of Online Training and its Relation to Engagement and Problem-solving Outcomes. Schöbel, Sofia; Janson, Andreas; Hopp, Jennifer Christin; Leimeister, Jan Marco. In Academy of Management Annual Meeting (AOM). 2019.
- [ URL ]
- [ BibSonomy-Post ]
A Configurational View on Avatar Design – The Role of Emotional Attachment, Satisfaction, and Cognitive Load in Digital Learning. Schöbel, Sofia; Janson, Andreas; Mishra, Abhay Nath. In International Conference on Information Systems (ICIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In online learning settings interactive and meaningful feedback is becoming increasingly important. However, feedback from teachers is oftentimes missing in online learning settings. To overcome challenges that arise from the missing representation of teachers, our study analyzes the relevance of avatar designs in learning settings. We therefore rely on avatars as game design elements and analyze how their design can influence emotional attachment, learning process satisfaction, and extraneous cognitive load in learning. To achieve our goal, we conduct a qualitative comparative analysis with 998 datasets that were collected in a 2x2x2 pre-post online experiment that was developed to train participants in learning functions in Excel. Our results indicate that interaction, familiarity, motivation, and aesthetic experiences are important configurations for avatars that are used in learning. We contribute to different streams of theory such as self-expansion and guide practitioners by providing implications about how to create meaningful avatar designs for learning applications.
Ansatz zur Umsetzung von Datenschutz nach der DSGVO im Arbeitsumfeld: Datenschutz durch Nudging. Schomberg, Sabrina; Barev, Torben Jan; Janson, Andreas; Hupfeld, Felix. In Informatik 2019 - 49. Jahrestagung der Gesellschaft für Informatik (GI). Gesellschaft für Informatik (GI), Kassel, Germany, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Die noch recht neue DSGVO hat einige Änderungen mit sich gebracht, welche sich in der Praxis erst noch bewähren und innovativ umgesetzt werden müssen. Insbesondere das Arbeitsumfeld wird von der fortschreitenden Digitalisierung stark verändert und sieht sich neuen Herausforderungen des Datenschutzes gegenüber. Ein Ansatz diesen Herausforderungen zu begegnen könnte die Integration von Privacy Nudges in digitale betriebliche Systeme sein. Ziel von Privacy Nudges ist es dabei den Entscheidungsprozess in digitalen Entscheidungsumgebungen gezielt zu mehr Schutz von personenbezogenen Daten und Privatheit zu beeinflussen. Diesem Ansatz nähert sich dieser Beitrag interdisziplinär, durch Erkenntnisse aus der verhaltensökonomischen, informatischen und der rechtswissenschaftlichen Literatur. Schließlich werden verschiedene Szenarien für den Einsatz von Privacy Nudges in digitalen Arbeitssystemen beschrieben und bewertet.
Generative Adversarial Networks for Operational Scenario Planning of Renewable Energy Farms: A Study on Wind and Photovoltaic. Schreiber, Jens; Jessulat, Maik; Sick, Bernhard. In Artificial Neural Networks and Machine Learning -- ICANN 2019: Image Processing, Bd. 11729, I. V. Tetko, V. Kurkova, P. Karpov, F. Theis (Hrsg.), S. 550–564. Springer International Publishing, Cham, 2019.
- [ BibSonomy-Post ]
Transfer Learning is a Crucial Capability of Intelligent Systems Self-Integrating at Runtime. Stein, A.; Tomforde, S. In 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W), S. 32–35. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Explicit Consideration of Resilience in Organic Computing Design Processes. Tomforde, S.; Gelhausen, P.; Gruhl, C.; Haering, I.; Sick, B. In ARCS Workshop 2019; 32nd International Conference on Architecture of Computing Systems, S. 1–6. 2019.
- [ BibSonomy-Post ]
Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning. Vogt, Stephan; Braun, Axel; Dobschinski, Jan; Sick, Bernhard. In Digital Proceedings of the 18th Wind Integration Workshop, U. Betancourt, T. Ackermann (Hrsg.). Dublin, Ireland, 2019.
- [ BibSonomy-Post ]
Towards Designing an Adaptive Argumentation Learning Tool. Wambsganss, Thiemo; Rietsche, Roman. In International Conference on Information Systems (ICIS). 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Digitalization triggers a shift in the compositions of skills and knowledge needed for students in their future work life. Hence, higher order thinking skills are becoming more important to solve future challenges. One subclass of these skills, which contributes significantly to communication, collaboration and problem-solving, is the skill of how to argue in a structured, reflective and well-formed way. However, educational organizations face difficulties in providing the boundary conditions necessary to develop this skill, due to increasing student numbers paired with financial constraints. In this short paper, we present the first steps of our design science research project on how to design an adaptive IT-tool that helps students develop their argumentation skill through formative feedback in large-scale lectures. Based on scientific learning theory and user interviews, we propose preliminary requirements and design principles for an adaptive argumentation learning tool. Furthermore, we present a first instantiation of those principles.
A chatbot dialogue model: Understanding human-chatbot collaboration in a complex task environment. Weingart, Pablo; Winkler, Rainer; Söllner, Matthias. In 14th International Conference on Wirtschaftsinformatik (WI). 2019.
- [ Abstract ]
- [ BibSonomy-Post ]
The rise of massive open online courses (MOOC) provides means to economize and scale education in response to higher budget restrictions [1] and raises the number of possible enrolled students by an unprecedented amount, compared to traditional higher education courses [2]. However, a disadvantage of MOOCs is the lack of individual support which can’t be addressed economically to a massive audience, often resulting in a less than optimal learning outcome [3]. Chatbots have the potential to alleviate this issue as a supporting tool to help the user learn how to solve a complex set of problems [4]. In 2017, the use of smart assistants in U.S. households like Amazon Echo or Google Home has increased by 128.9 per cent. Future forecasts indicate that their use will likely rise so that by 2022 the majority of the U.S. households will have at least one smart assistant in their home [5]. Chatbots have been around since at least 1966 [6], yet their use in more complex settings currently still involves difficulties, as interactions between users and chatbots remain for the most part simple and usually follow a simple question answer approach [7]. The application of advanced technologies such as deep learning [8] and the recently unveiled Google Duplex, a more technologically advanced smart assistant, already hints in a direction where in the near future smart assistants can act as collaboration partner in solving more complex tasks [9]. However, this remains a research field which is only beginning to unfold, with none or little research taken to how chatbot user interaction can be structurally developed within a problem task scenario. Thus, the aim of this paper is to design a process model on how chatbots and users can collaborate together in order to solve a problem. This model helps chatbot designers to analyze human-chatbot interactions and derive design requirements from it.
Alexa, Can You Help Me Solve That Problem? - Understanding the Value of Smart Personal Assistants as Tutors for Complex Problem Tasks. Winkler, Rainer; Bittner, Eva A. C.; Söllner, Matthias. In 14th International Conference on Wirtschaftsinformatik (WI), T. Ludwig, V. Pipek (Hrsg.), S. 371–376. University of Siegen, Germany / AISeL, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In recent decades, the number of students per lecturer at universities has constantly risen. In these learning scenarios, individual lecturer support for helping students actively acquiring new knowledge is hardly possible. However, active student behavior is necessary for successful learning. Smart Personal Assistants such as Amazon’s Alexa or Google’s Home promise to fill this gap by being students’ individual tutors. In order to understand what students expect from Smart Personal Assistants as tutors and how they interact with them, we will carry out an experiment. In this research in progress paper, we present our experiment design, where we observe the individual interaction between students and a Smart Personal Assistant tutor and between students and a human tutor applying the same methods in both cases. Drawing on the concepts of parasocial interaction and trust, we derive hypotheses, present the Smart Personal Assistant development and explain the experiment process in detail.
Towards a Technique for Modeling New Forms of Collaborative Work Practices – The Facilitation Process Model 2.0. Winkler, Rainer; Briggs, Robert O.; De Vreede, Gert-Jan; Leimeister, Jan Marco; Oeste-Reiß, Sarah; Söllner, Matthias. In Hawaii International Conference on System Sciences (HICSS). Maui, Hawaii, USA, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Collaboration Engineering (CE) is an approach for the design and deployment of repeatable collaborative work practices that can be executed by practitioners themselves without the ongoing support of external collaboration professionals. A key design activity in CE concerns modeling current and future collaborative work practices. CE researchers and practitioners have used the Facilitation Process Model (FPM) technique. However, this modeling technique suffers from a number of shortcomings to model contemporary collaborative work practices. We use a design science approach to identify the main challenges with the original FPM technique, derive requirements and design a revised modeling technique that is based on the current technique enriched by BPMN 2.0 elements. This paper contributes to the CE literature by offering a revised FPM technique that assists CE-designers to capture new forms of collaborative work practices.
Improving Problem-Solving Skills with Smart Personal Assistants: Insights from a Quasi Field Experiment. Winkler, Rainer; Büchi, Claudio; Söllner, Matthias. In International Conference on Information Systems (ICIS), H. Krcmar, J. Fedorowicz, W. F. Boh, J. M. Leimeister, S. Wattal (Hrsg.). Association for Information Systems, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Problem-solving skills are considered one of the most important learning goals for life. Therefore, educational institutions should help learners gain these skills despite organizational and financial restrictions. Even though there exists a growing body of research about the design and use of Smart Personal Assistants, such as Google’s Assistant or Amazon’s Alexa, little is known about their ability to help learners improve their problem-solving skills. Using a mixed-method approach, we investigate the value of newly emerging Smart Personal Assistants to improve long-term problem solving skills with the help of a pre- and post-test quasi field experiment in a second grade class of a vocational business school in Switzerland. The results indicate that groups interacting with Smart Personal Assistants show significantly better problem-solving skills compared to learners using paper-based support explained by changing learning processes. Our study contributes to existing intelligent tutoring system and technology-enhanced scaffolding research.
Hey Alexa, Please Help Us Solve This Problem! How Interactions with Smart Personal Assistants Improve Group Performance. Winkler, Rainer; Neuweiler, Maya Lisa; Bittner, Eva A. C.; Söllner, Matthias. In International Conference on Information Systems (ICIS), H. Krcmar, J. Fedorowicz, W. F. Boh, J. M. Leimeister, S. Wattal (Hrsg.), S. 6. ACM Digital, 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Despite a growing body of research about the design and use of Smart Personal Assistants, such as Google’s Assistant or Amazon’s Alexa, existing work has mainly focused on their use as task support for individual users in rather simple problem scenarios. Little is known about their ability to improve collaboration among multiple users in more complex problem settings. Using a mixed-method approach, we investigate the value of Smart Personal Assistants as facilitators by directly comparing 40 groups of three who either interact with a Smart Personal Assistant or a scripted human facilitator in a complex problem-solving scenario. The results indicate that groups interacting with Smart Personal Assistant facilitators show significantly better task outcomes and higher degrees of collaboration quality. A conversation analysis approach further analyzes differences in human SPA communication. Our work contributes to computer-supported cooperative work research and emphasizes the value of conversation analysis approaches in HCI research.
Alexa, Can You Help Us Solve This Problem? How Conversations With Smart Personal Assistant Tutors Increase Task Group Outcomes. Winkler, Rainer; Söllner, Matthias; Neuweiler, Maya Lisa; Rossini, Flavia Conti; Leimeister, Jan Marco. In Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. ACM, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Despite a growing body of research about the design and use of Smart Personal Assistants, existing work has mainly focused on their use as task support for individual users in rather simple problem scenarios. Less is known about their ability to improve collaboration among multiple users in more complex problem settings. In our study, we directly compare 21 groups who either use a Smart Personal Assistant tutor or a human tutor when solving a problem task. The results indicate that groups interacting with Smart Personal Assistant tutors show significantly higher task outcomes and higher degrees of collaboration quality compared to groups interacting with human tutors. The results are used to suggest areas for future research in the field of computer-supported collaboration.
When Indoor Localization Meets New Communication Technologies. Xu, Y.; David, K. In 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), S. 1–4. IEEE, Honolulu, Hawaii, USA, 2019.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Accurate and low-cost indoor localization continues to be a research challenge. The emerging communication technologies in 5G and 802.11 standards (e.g., 802.11n and 802.11 ac), such as massive MIMO and mmWave, provide opportunities for accurate indoor localization. Meanwhile, location information is also critical for the development of new technologies, e.g., directional communication using beamforming. It leads to a synergistic relationship between localization and communication. In this paper, we review the potential benefits of the emerging communication technologies (i.e., smart antennas, Massive MIMO, mmWave, beamforming, CSI) for indoor localization. It may provide a useful guide for researchers who are interested in developing indoor localization systems based on emerging communication technologies.
Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks. Zernetsch, S.; Reichert, H.; Kress, V.; Doll, K.; Sick, B. In 2019 IEEE Intelligent Vehicles Symposium (IV), S. 810–815. 2019.
- [ DOI ]
- [ BibSonomy-Post ]
Vision: Shining Light on Smart Homes – Supporting Informed Decision-Making of End Users. Zimmermann, Verena; Dickhaut, Ernestine; Gerber, Paul; Vogt, Joachim. In IEEE Institute of Electrical and Electronics Engineers. 2019.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Smart Home technologies are promising to enhance quality of life, autonomous living of elderly people and home security. Yet, uncertainty in terms of personal benefits, functionality, cost, privacy and security features influences potential users' decision processes. The vision of this research thus is to support end users' informed decision-making in terms of Smart Home technologies. We developed and tested a prototype of an interactive Smart Home configurator that provides users with targeted information according to their interests. It visualizes Smart Home processes and implications for privacy and security to increase transparency and reduce uncertainty in the decision-process. Ideas for further improving and extending the concept of the Smart Home configurator are discussed.
Explaining Business Process Software with Fulib-Scenarios. Zuendorf, Albert; Copei, Sebastian; Diethelm, Ira; Draude, Claude; Kunz, Adrian; Norbisrath, Ulrich. Bd. Workshop proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019). 2019.
- [ BibSonomy-Post ]

2018[ to top ]

Ad-Hoc-Kommunikation – Gesellschaftlich wünschenswert, rechtlich ungeregelt. Almon, Lars; Álvarez, Flor; Lieser, Patrick; Meuser, Tobias; Schaller, Fabian. In Die Fortentwicklung des Datenschutzes., Bd. Springer, A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 77–98. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Analyzing Group Interaction on Networks of Face-to-Face Proximity using Wearable Sensors. Atzmueller, Martin; Thiele, Lisa; Stumme, Gerd; Kauffeld, Simone. In Proc. IEEE International Conference on Future IoT Technologies. IEEE Press, Boston, MA, USA, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Towards Value Proposition Mining – Exploration of Design Principles. Augenstein, Dominik; Fleig, Christian; Dellermann, Dominik. In International Conference on Information Systems (ICIS). 2018.
- [ URL ]
- [ BibSonomy-Post ]
The Wireless Seat Belt Requirements, Experiments, and Solutions for Pedestrian Safety. Bachmann, Marek; Morold, Michel; David, Klaus. In Proceedings of the 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), S. 250 – 255. IEEE, Athens, Greece, 2018.
- [ BibSonomy-Post ]
„Die Fortentwicklung des Datenschutzes“. Bieker, Felix; Geminn, Christian. In „Zur künftigen Fortentwicklung des Datenschutzes“, A. Roßnagel, M. Friedewald, M. Hansen (Hrsg.), S. 407–414. Springer Vieweg, Wiesbaden, 2018.
- [ BibSonomy-Post ]
Zur künftigen Fortentwicklung des Datenschutzes. Bieker, Felix; Geminn, Christian. In Die Fortentwicklung des Datenschutzes., A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 387–394. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Where is my Device? Detecting the Smart Device’s Wearing Position in the Context of Active Safety for Vulnerable Road Users. Bieshaar, M. In Organic Computing: Doctoral Dissertation Colloquium, S. Tomforde, B. Sick (Hrsg.). Kassel University Press, 2018.
- [ BibSonomy-Post ]
Starting Movement Detection of Cyclists Using Smart Devices. Bieshaar, M.; Depping, M.; Schneegans, J.; Sick, B. In DSAA. Turin, Italy, 2018.
- [ BibSonomy-Post ]
Developing And Implementing Citizen-initiated Services. Billert, Matthias Simon. In International Conference on Exporing Service Science (IESS). 2018.
- [ Abstract ]
- [ BibSonomy-Post ]
Most citizen participation concepts in city administrations are not sufficiently developed and stop at the idea phase of service engineering, which leads to challenges for administrations. However, top-down approaches of the government fail because citizens do not accept the invitation to participate and bottom-up approaches of citizen initiatives claim the attention and support of administrations. To counteract this, citizens are involved as experts of their everyday life. Following design science research, we iteratively build the “digitalization street”, which is a portal that systematically guides the citizens through the development of own services. For a formative and artificial evaluation, we used a framework with a human risk and effectiveness strategy. Thus, we contribute to the existing body of knowledge by systematically reconditioned knowledge about citizen sensing and we exhibit requirements for guidelines concerning how citizens can develop own services that can be implemented in the city administrations.
Grinding A Diamond - The Iterative Development of Citizen-Initiated Services. Billert, Matthias Simon; Peters, Christoph. In European Conference on Information Systems (ECIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Many city administrations follow the smart city concept to grasp the potential of citizen participation. However, most participation concepts are not developed thoroughly, this leading to unexploited poten-tial. Citizens are experts of their everyday life and are best aware of their personal needs. However, current forms of citizen participation stop at the idea phase of service engineering. Following design science research, we iteratively build and evaluate a so-called “digitalization street” which aims to systematically guide the citizens through the refinement and further development of their services. This digitalization street is implemented in a mid-size European city and integrates five modules which let citizens (1) describe their project proposal, (2) concretise according strengths, weaknesses, opportuni-ties and threats, (3) identify the gain creators and pain relievers, (4) create their solution, (5) present their solution. Based on literature and a requirement elicitation workshop, a first instantiation of the artefact was developed. We contribute to the existing body of knowledge by presenting a framework for creating services based on a citizen-centric approach. We exhibit how the digitalization street can be implemented into existing processes in the city administration and help to increase the citizen par-ticipation from a project to an evaluated prototype.
Knowing what Learners Like – Developing a Cultural Sensitive Peer Assessment Process in MOOCs. Buholzer, Fabienne; Rietsche, Roman; Söllner, Matthias. In Multikonferenz Wirtschaftsinformatik (MKWI). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
MOOCs attract learners from various cultural backgrounds with differing educational beliefs and learning preferences. Research has long acknowledged that culture has an impact on the adoption and use of information technology. Cultural differences can cause conflicts, especially when learners provide each other with feedback during the peer assessment process. With this paper, we use a design science approach to create a cultural sensitive peer assessment process in MOOCs. Based on Hofstede’s cultural dimension theory we derive design elements and evaluate them in a qualitative and comparative study with Swiss and Chinese students. Our results show that different cultures prefer different designs. Consequently, our key contribution is the practical elaboration of design elements, which can be integrated in MOOCs to provide a better learning experience. Further, we contribute to cross-cultural theory by using an existing framework and adapting it to a new and relevant phenomenon: MOOCs.
Analyse offener Datenquellen durch die Polizei: Entgrenzte Internet- und Darknetaufklärung in der Strafverfolgung?. C. Johannes, Paul. In Die Fortentwicklung des Datenschutzes., A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 151–174. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Decision Support with Hybrid Intelligence. Calma, Adrian; Dellermann, Dominik. In International Organic Computing (DDC). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Startups are the fresh blood of our economy and, besides uni- versities, are thriving innovation. One of the rst steps in this enriching journey to success, where they create jobs and new products, is getting funded. Decision makers, such as investors, incubators, and accelerators, receive a large amount of funding proposals. Currently, new ventures are evaluated "manually", often without any machine learning or any decision support at all. The implicit rules that every experienced decision maker has developed through years of failures and successes can not be codied, let alone be explained. It is intuition. We envision a learning system that is able to learn the intuition from multiple decision makers and guide them in their judgment. Our envisioned learning system relies on hybrid intelligence, which we dene as the ability to accomplish complex goals by combining human and articial intelligence to collectively achieve superior results and continuously improve by learning from each other.
A Concept for Productivity Tracking based on Collaborative Interactive Learning Techniques. Calma, Adrian; Kuhn, Jochen; Leimeister, Jan Marco; Lukowicz, Paul; Oeste-Reiß, Sarah; Schmidt, Albrecht; Sick, Bernhard; Stumme, Gerd; Tomforde, Sven; Zweig, Anna Katharina. In International Conference on Architecture of Computing Systems (ARCS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The academic success of individual students differs widely and it depends on various factors, ranging from financial to social and to health aspects. In this article, we propose a concept for a novel productivity tracking system that provides the basis for a self-assessment of academic behaviour and that can be used by students to support their academic success. The development of such a system requires interdisciplinary efforts, most of them located in the field of collaborative interactive learning (CIL) that is grounded on a socio-technical system perspective. The system is interactive since it is based on bidirectional communication, collaborative in the sense that it uses students, other students, and external sources such as the Internet for generation of knowledge, and learning in the sense that it continuously and autonomously acquires knowledge. It is further self-organised as it decides about interaction partners and self-adaptive in terms of modifying its behaviour according to changing conditions.
Leveraging the Potentials of Dedicated Collaborative Interactive Learning: Conceptual Foundations to Overcome Uncertainty by Human-Machine Collaboration. Calma, Adrian; Oeste-Reiß, Sarah; Sick, Bernhard; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS), S. 960–968. Waikoloa, HI, USA, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Active Learning with Realistic Data -- A Case Study. Calma, Adrian; Stolz, Moritz; Kottke, Daniel; Tomforde, Sven; Sick, Bernhard. In International Joint Conference on Neural Networks. Rio de Janiero, Brazil, 2018.
- [ BibSonomy-Post ]
Coopetitive Soft Gating Ensemble. Deist, S.; Bieshaar, M.; Schreiber, J.; Gensler, A.; Sick, B. In Workshop on Self-Improving System Integration (SISSY). Trento, Italy, 2018.
- [ BibSonomy-Post ]
Accelerating Decisional Guidance in Entrepreneurship with Hybrid Intelligence. Dellermann, Dominik. In International Conference on Information Systems (ICIS). 2018.
- [ Abstract ]
- [ BibSonomy-Post ]
Decision making in the context of entrepreneurship is a highly complex task. For dealing with such uncertain problems, decisional guidance proved to be a valuable approach to support entrepreneurs in making decisions. Mentoring and feedback from human experts and simple statistical methods emerge as dominant forms of providing decisional guidance. However, both individual human experts and existing decision support systems (DSS) have limited capabilities to provide optimal decisional guidance in such highly uncertain settings. While human experts have cognitive and resource constraints that prevent them from providing optimal guidance, computational DSS are frequently to deal with such complex problems. Consequently, the purpose of this dissertation is to provide prescriptive knowledge for novel forms of decisional guidance that support entrepreneurial decision makers by proposing collective intelligence and crowdsourcing (effective) as well as hybrid intelligence (effective and efficient) mechanism for efficient and effective decisional guidance. Following a design science research approach, I develop several artefacts such as system architectures and DSSs that are evaluated and provide innovative design knowledge for hybrid intelligence IS. The contribution of this dissertation is threefold. First, I provide an in-depth exploration of decisional guidance and its limitations in entrepreneurial decision making. Second, I propose collective intelligence and IT enabled crowdsourcing as a novel mechanism to guide entrepreneurs in creating their opportunities. Third, I conceptually develop hybrid intelligence as novel forms for making predictions under uncertainty. My research therefore provides prescriptive knowledge on the design of such hybrid intelligence architectures that are capable to predict uncertain outcomes. Finally, my results point towards a new class of DSS that might be particularly valuable in highly uncertain contexts.
Making AI Ready for the Wild- the Hybrid Intelligence Unicorn Hunter. Dellermann, Dominik; Calma, Adrian. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Managing the Dark Side of Software Ecosystems. Dellermann, Dominik; Jud, Christopher; Lipusch, Nikolaus; Popp, Karl Michael. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
A Complementor ́s Perspective on Co-Innovation Risk. Dellermann, Dominik; Lipusch, Nikolaus. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
The Future of Entrepreneurship: Crowd-Based Incubation. Dellermann, Dominik; Lipusch, Nikolaus; Ebel, Philipp. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Integrating Your Ecosystem with the Hybrid Intelligence Accelerator. Dellermann, Dominik; Lipusch, Nikolaus; Ebel, Philipp. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Heading for new shores: Crowdsourcing for entrepreneurial opportunity creation. Dellermann, Dominik; Lipusch, Nikolaus; Ebel, Phlipp. In European Conference of Information Systems (ECIS). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Combining Humans and Machine Learning: A Novel Approach for Evaluating Crowdsourcing Contributions in Idea Contests. Dellermann, Dominik; Lipusch, Nikolaus; Li, Mahei. In Multikonferenz Wirtschaftsinformatik (MKWI). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
The creative potential from innovative contributions of the crowd constitutes some critical challenges. The quantity of contributions and the resource demands to identify valuable ideas is high and remains challenging for firms that apply open innovation initiatives. To solve these problems, research on algorithmic approaches proved to be a valuable way by identifying metrics to distinguish between high and low-quality ideas. However, such filtering approaches always risk missing promising ideas by classifying good ideas as bad ones. In response, organizations have turned to the crowd to not just for generating ideas but also to evaluate them to filter high quality contributions. However, such crowd-based filtering approaches tend to perform poorly in practice as they make unrealistic demands on the crowd. We, therefore, conduct a design science research project to provide prescriptive knowledge on how to combine machine learning techniques with crowd evaluation to adaptively assign humans to ideas.
Clones in Graphs. Doerfel, Stephan; Hanika, Tom; Stumme, Gerd. In ISMIS, Bd. 11177 von Lecture Notes in Computer Science, M. Ceci, N. Japkowicz, J. Liu, G. A. Papadopoulos, Z. W. Ras (Hrsg.), S. 56–66. Springer, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Acceptability by Design: Integrating Gender Research in HCI. Draude, Claude; Klumbyte, Goda. In Proceedings of CHI’18 Workshop on (Un)Acceptable!?! – Re-thinking the Social Acceptability of Emerging Technologies, M. Koelle, H. Proﬁta, T. Olsson, R. Mitchell, J. Williamson, S. Kane, S. Boll (Hrsg.). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Re-Considering Bias: What Could Bringing Gender Studies and Computing Together Teach Us About Bias in Information Systems?. Draude, Claude; Klumbyte, Goda; Treusch, Pat. In Proceedings of International Workshop on Bias in Information, Algorithms, and Systems co-located with 13th International Conference on Transforming Digital Worlds (iConference 2018), J. Bates, P. D. Clough, R. Jäschke, J. Otterbacher (Hrsg.). CEUR Workshop Proceedings, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Making IT Work: Integrating Gender Research in Computing Through a Process Model. Draude, Claude; Maaß, Susanne. In Proceedings of the 4th Conference on Gender & IT, von GenderIT ’18, S. 43–50. ACM, Heilbronn, Germany, 2018.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
To become effective in the field of computing, gender research must explain its concepts to non-gender studies scholars and to convince them of their relevance. Our title "Making IT Work" claims that both can be done: interlinking gender research and computing, and by that improving IT systems. We present the "Gender-Extended Research and Development" (GERD) model, a process model which combines gender and diversity aspects with all phases of computing research and development. The model with seven phases is a generalization of common process models in computing. Gender/diversity expertise has been condensed into a number of aspects that characterize the social context of computing research. They can be related to and reflected during every phase. This reflection is somewhat operationalized by providing a list of questions for each combination of phase and aspect. Case studies as part of the model illustrate either in what way such reflections may help in research and development or what may happen if no such aspects have been included.
Comparing the Performance of Wi-Fi Fingerprinting Using the 2.4 GHz and 5 GHz Signals. Duong, Doan; Xu, Yaqian; David, Klaus. In Proceedings of the 2018 IEEE 87th Vehicular Technology Conference (VTC Spring), S. 1–5. IEEE, Porto, Portugal, 2018.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Wi-Fi fingerprinting is a promising technique for indoor localization. The use of both 2.4 GHz and 5 GHz for Wi-Fi fingerprinting has been preliminarily studied by some research groups. However, most of the previous studies only consider the reflection and multi-paths caused by walls around but do not consider the damping and scattering through walls between them. In this paper, we particularly consider the situation that the radio propagation covers several rooms divided by walls, and compare the localization performance of using 2.4 GHz and 5 GHz networks. Moreover, we also compare the power consumption of scanning the surrounding wireless channels used for 2.4 GHz and 5 GHz networks. The results show that the performance of accuracy of Wi-Fi fingerprinting is similar when using 2.4 GHz and 5 GHz respectively. However, the use of 5 GHz results in higher response rate, while the use of 2.4 GHz consumes less power.
The Influence of Fast Fading and Device Heterogeneity on Wi-Fi Fingerprinting. Duong, Doan; Xu, Yaqian; David, Klaus. In Proceedings of the 2018 IEEE 87th Vehicular Technology Conference (VTC Spring), S. 1–5. IEEE, Porto, Portugal, 2018.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
As Wi-Fi fingerprinting is a promising approach for indoor localization, one of the major challenges is understanding how fast fading and device heterogeneity problems influence the performance of the Wi-Fi fingerprinting systems. In this paper, we experimentally investigate the influence of fast fading and the device heterogeneity problems on the Wi-Fi RSS values, as well as on the performance (i.e., the recognition rate) of a Wi-Fi fingerprinting system WHERE. Besides, we also compare the performance of Wi-Fi fingerprinting in the experimental scenarios and in the real scenarios with the consideration of the fast fading problem. It concludes that both fast fading and device heterogeneity heavily influences the RSS values. However, the influence of fast fading on the performance of the Wi-Fi fingerprinting system can be mitigated when the Wi-Fi data is collected in the real scenarios.
Understanding Job Satisfaction of Crowd Workers: An Empirical Analysis of Its Determinants and Effects. Durward, David; Blohm, Ivo. In Multikonferenz Wirtschaftsinformatik (MKWI). Lüneburg, Germany, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowd work has emerged as new pattern of digitally mediated collaboration. In this paper, we focus on the determinants and effects of crowd workers’ job satisfaction – a perspective that has been largely neglected by current crowdsourcing research. We report results from a survey of 161 crowd workers participating in crowdsourced software testing. Our research shows that job satisfaction mediates the effects of monetary rewards, hedonic value, and cognitive stimulation on the intention to participate in future testing tasks. By contrast, factors of work context (i.e., flexibility and provided information) have no effects. We contribute to the literature by unraveling job satisfaction as causal mechanism influencing future participation. For practice, our results help to design more effective tasks in crowd work.
How Digital Nudges Influence Consumers - Experimental Investigation in the Context of Retargeting. Eigenbrod, Laura; Janson, Andreas. In European Conference on Information Systems (ECIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Retargeting is an innovative online marketing technique in the modern age. Although this advertising form offers great opportunities of bringing back customers who have left an online store without a com-plete purchase, retargeting is risky because the necessary data collection leads to strong privacy con-cerns which, in turn, trigger consumer reactance and decreasing trust. Digital nudges – small design modifications in digital choice environments which guide peoples’ behaviour – present a promising concept to bypass these negative consequences of retargeting. In order to prove the positive effects of digital nudges, we aim to conduct an online experiment with a subsequent survey by testing the impacts of social nudges and information nudges in retargeting banners. Our expected contribution to theory includes an extension of existing research of nudging in context of retargeting by investigating the effects of different nudges in retargeting banners on consumers’ behaviour. In addition, we aim to provide practical contributions by the provision of design guidelines for practitioners to build more trustworthy IT artefacts and enhance retargeting strategy of marketing practitioners.
How Digital Nudges Influence Consumers – The Role of Social and Privacy Nudges in Retargeting. Eigenbrod, Laura; Janson, Andreas; Leimeister, Jan Marco. In Academy of Management Annual Meeting (AOM). 2018.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Retargeting is an innovative online marketing technique because it can provide consumer-specific advertising content based on consumers’ browsing behavior that meet consumers' prefer-ences and interests. Although this advertising form offers great opportunities of bringing back customers who have left an online store without to complete a purchase, retargeting is risky be-cause the necessary data collection leads to strong privacy concerns which in turn, trigger con-sumer reactance and decreasing trust. Digital nudges – small design modifications in digital choice environments which guide peoples’ behavior – present a promising concept to bypass these negative consequences of retargeting. In order to explore the positive effects of digital nudges in retargeting banners, we conducted a between-subject experiment with a subsequent survey which examines the impacts of social nudges (likes of friends) and privacy nudges (disclosure of privacy policy and purpose of retargeting banners). Whereas the social nudge led to a negative impact on consumers’ privacy concerns and a positive impact on consumers’ booking behavior, the privacy nudge did not have any significant impact. A combination of social nudge and privacy nudge showed that the privacy nudge negatively moderated the positive relationship between social nudge and consumers’ booking behavior. The derived implications provide a theory for under-standing nudges in digital environments and we offer design principles for practitioners that enable better retargeting outcomes.
Schwimmen oder Untergehen - Informationsüberflutung durch E-Mails im Arbeitsalltag. Friedrichs, Juliane; Ohly, Sandra; Duranova, Lenka. In Presentation at the 51. Kongress der Deutschen Gesellschaft für Psychologie (DGPs) in Frankfurt, S. 52. 2018.
- [ BibSonomy-Post ]
Übersicht zu Lernplattformen für die berufliche Weiterbildung. Funk, J.; Eis, A.; Schmidt, L. In ARBEIT(s).WISSEN.SCHAF(f)T - Grundlage für Management & Kompetenzentwicklung: 64. Kongress der Gesellschaft für Arbeitswissenschaft (Frankfurt am Main 2018), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (C.3.5). GfA-Press, Dortmund, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Eine große Anzahl an verfügbaren Lernplattformen und eine stetige Veränderung des Markts durch neue Anbieter erschweren die Auswahl eines geeigneten Systems. Für eine Marktübersicht wurde eine Literatur- und Internetrecherche von verfügbaren Lernplattformen durchgeführt. Die Rechercheergebnisse wurden aussagefähigen Kategorien wie bspw. Administration, Didaktik, Kommunikation oder Technik zugeordnet. Durch die Unterteilung der Lernplattformen in Kategorien lassen sich die Rechercheergebnisse schnell anhand eigener Anforderungen filtern, um geeignete Plattformen für bestimmte Anforderungen zu identifizieren. Die Recherche ergab, dass sich einige Produktmerkmale, bspw. die mobile Zugänglichkeit von E-Learning-Material, als Basiseigenschaften etabliert haben, wohingegen VR-/AR-Technologien bisher nicht berücksichtigt werden.
Blickbewegungsstudie zu Orientierung und Informationsbedarf beim Verkehrsmittelwechsel am Frankfurter Flughafen. Funk, J.; Klose, E. M.; Schmidt, L. In ARBEIT(s).WISSEN.SCHAF(f)T - Grundlage für Management & Kompetenzentwicklung: 64. Kongress der Gesellschaft für Arbeitswissenschaft (Frankfurt am Main 2018), Gesellschaft für Arbeitswissenschaft e. V. (Hrsg.), S. 1–6 (B.1.2). GfA-Press, Dortmund, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die vorliegende Studie untersucht, woran sich Menschen an komplexen Verkehrsknotenpunkten orientieren und welche Probleme hierbei auftreten. Dafür wurden die Blickbewegung gemessen und die Schritte gezählt, während die zwölf Teilnehmer drei Navigationsaufgaben durch den Frankfurter Flughafen absolvierten. Anschließend wurde die Retrospektive Think-Aloud-Methode genutzt, um einen Einblick in Gedanken und Strategien der Probanden zu bekommen. So konnten Problemstellen, wie z. B. die Suche auf Übersichtsplänen oder das Bestimmen der derzeitigen Etage, identifiziert werden, aus denen Gestaltungsempfehlungen für eine Fußgängernavigation mit Datenbrillen abgeleitet werden.
Aspects of Measuring and Evaluating the Integration Status of a (Sub-)System at Runtime. Gruhl, Christian; Tomforde, Sven; Sick, Bernhard. In 2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W), Trento, Italy, September 3-7, 2018, S. 198–203. 2018.
- [ BibSonomy-Post ]
Towards Collaborative Conceptual Exploration. Hanika, Tom; Zumbrägel, Jens. In ICCS, Bd. 10872 von Lecture Notes in Computer Science, P. Chapman, D. Endres, N. Pernelle (Hrsg.), S. 120–134. Springer, 2018.
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
A Decentralized Resilient Short-Term Cache for Messaging. Heck, Henner; Kieselmann, Olga; Kopal, Nils; Wacker, Arno. In IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS), Bd. 10853 von Lecture Notes in Computer Science, S. 110–121. Springer, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Messaging applications are among the most popular internet applications and people use them worldwide on a daily basis. Their supporting infrastructure, though consisting of a multitude of servers, is typically under central control. This enables censorship and seamless user profiling. A fully decentralized infrastructure, with decentralized control and redundant data storage, can mitigate these dangers. In this paper we evaluate the basic ability of decentralized networks created by the network overlay and data storage protocol Kademlia to serve as a short-term data cache for messaging applications. Our results show, that reliable retrieval of up to 20 replicas is possible.
Security Issues in Self-Improving System Integration - Challenges and Solution Strategies. Heck, Henner; Sick, Bernhard; Tomforde, Sven. In 2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W), Trento, Italy, September 3-7, 2018, S. 176–181. 2018.
- [ BibSonomy-Post ]
CAVE-basierte Nutzerstudie eines Aufenthalts-Empfehlungssystems. Hegenberg, J.; Kannengießer, N.; Klose, E.; Schmidt, L. In Mensch und Computer 2018 - Tagungsband (Dresden 2018), R. Dachselt, G. Weber (Hrsg.), S. 117–128. Gesellschaft für Informatik e. V, Bonn, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Reiseassistenzsysteme sind vielversprechend, um individualisierte und kontextbezogene Unterstützung entlang intermodaler Reiseketten im öffentlichen Verkehr anzubieten. Hierbei stellen sowohl zeitkritische Situationen als auch solche mit längerer Wartezeit eine Belastung des Reisenden dar. Für letztere bietet das untersuchte System Assistenz durch individualisierte Gestaltungsvorschläge für längere Aufenthalte. In Vorbereitung auf eine großangelegte Feldstudie wurden vier Varianten des zugrundeliegenden Empfehlungssystems und ein Trainingsansatz zur Initialisierung des Nutzerprofils hinsichtlich der numerischen und der subjektiv wahrgenommenen Genauigkeit der Empfehlungen evaluiert. Die Benutzungsschnittstelle in einer optischen Durchsichtdatenbrille wird außerdem hinsichtlich ihrer Gebrauchstauglichkeit evaluiert. Für die Evaluation wurde eine Reise inkl. zweier längerer Aufenthalte mittels einer CAVE simuliert.
The Impact of Physical Activities on the Physiological Response to Emotions. Heinisch, Judith; Hübener, Isabel; David, Klaus. In Proceedings of the 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), S. 860 – 865. IEEE, Athens, Greece, 2018.
- [ BibSonomy-Post ]
Sampling Strategies for Representative Time Series in Load Flow Calculations. Henze, Janosch; Kutzner, Stephan; Sick, Bernhard. In Data Analytics for Renewable Energy Integration. Technologies, Systems and Society - 6th ECML PKDD Workshop, DARE 2018, Dublin, Ireland, September 10, 2018, Revised Selected Papers, S. 27–48. 2018.
- [ BibSonomy-Post ]
Active Sorting -- An Efficient Training of a Sorting Robot with Active Learning Techniques. Herde, Marek; Kottke, Daniel; Calma, Adrian; Bieshaar, Maarten; Deist, Stephan; Sick, Bernhard. In International Joint Conference on Neural Networks. Rio de Janiero, Brazil, 2018.
- [ BibSonomy-Post ]
Dynamische Zertifizierung – Der Weg zum verordnungskonformen Cloud Computing. Hofmann, Johanna M. In Die Fortentwicklung des Datenschutzes., A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 293–310. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Sind neue Technologien datenschutzrechtlich regulierbar? Herausforderungen durch „Smart Everything“. Hornung, Gerrit. In Die Fortentwicklung des Datenschutzes., A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 315–336. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
FeSNOC: A Novel Feature Selection Algorithm Based on Niche Overlapping Coefficient. Hübener, Isabel; David, Klaus. In Proceedings of the 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom), S. 165 – 171. IEEE, Athens, Greece, 2018.
- [ BibSonomy-Post ]
Hijacked Smart Devices -- Methodical Foundations for Autonomous Theft Awareness based on Activity Recognition and Novelty Detection. Jänicke, Martin; Schmidt, Viktor; Sick, Bernhard; Tomforde, Sven; Lukowicz, Paul. In Proceedings of the 10th International Conference on Agents and Artificial Intelligence. 2018.
- [ BibSonomy-Post ]
Smart Device Stealing and CANDIES. Jänicke, Martin; Schmidt, Viktor; Sick, Bernhard; Tomforde, Sven; Lukowicz, Paul; Schmeißing, Jörn. In Agents and Artificial Intelligence - 10th International Conference, ICAART 2018, Funchal, Madeira, Portugal, January 16-18, 2018, Revised Selected Papers, S. 247–273. 2018.
- [ BibSonomy-Post ]
Behavior-based Service Change Detection. Jahl, Alexander; Tran, Tam Huu; Baraki, Harun; Geihs, Kurt. In 4th IEEE International Conference on Smart Computing (SMARTCOMP). IEEE, 2018.
- [ BibSonomy-Post ]
5G Based Collision Avoidance - Benefit from Unobtrusive Activities. Jahn, Andreas; Morold, Michel; David, Klaus. In Proceedings of the 2018 European Conference on Networks and Communications (EuCNC), S. 352–356. IEEE, Ljubljana, Slovenia, 2018.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Every year many vulnerable road users (VRUs), such as pedestrians or bicyclists, are killed or seriously injured in traffic accidents. To reduce the number of such traffic accidents several research groups are working on different solutions. The approach presented in this paper is based on wireless communications such as WLAN and 5G/LTE and a “context filter.” The “context filter” identifies vulnerable road users in potentially dangerous situations based on several inputs (e.g., location, movement direction). An identified dangerous situation is communicated between VRUs and cars using wireless communication. As one interesting context for identifying dangerous situations, this paper investigates how to recognize pedestrians stepping onto the road. Utilizing smartphone sensor data, the investigated approaches address three key challenges: inconsistent sensor data, overrepresentation of periodic activities, as well as the evaluation of the recognition. For each challenge, a possible solution is proposed. The results indicate that recognizing the “stepping onto the road” is possible and support the overall 5G based collision avoidance system.
Towards Cooperative Self-adapting Activity Recognition. Jahn, Andreas; Tomforde, Sven; Morold, Michel; David, Klaus; Sick, Bernhard. In Proceedings of the 8th International Joint Conference on Pervasive and Embedded Computing and Communication Systems, PECCS 2018, Porto, Portugal, July 29-30, 2018., S. 215–222. 2018.
- [ BibSonomy-Post ]
Nudging Privacy in Digital Work Systems – Towards the Development of a Design Theory. Janson, Andreas; Schöbel, Sofia. In International Conference on Information Systems (ICIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Digitization changes our society, the way we work and the way we generate value in work systems. More precisely, it equally affects how business and employees organize their work. While there is a tremendous innovation potential for businesses such as more flexible and efficient work arrangements, there are also tremendous privacy risks. Such privacy risks especially relate to issues that employees leave data traces in every working step while being oftentimes not aware of their generated data. Employees leave data traces on intranet platforms such as Wikis and on external work tools such as Slack and reveal not only personal information but also company insights. At the same time companies must handle new privacy regulations such as the European General Data Protection Regulation (GDPR) which do not only affect companies in the European countries but also providers of information systems (IS) all around the world that offer their services in Europe. Thus, innovative approaches for considering challenges that exist because of privacy related issues are needed. A promising approach to overcome the aforementioned privacy issues of digital working environments is the application of digital nudges in IS – small design modifications in digital choice environments which guide peoples’ behavior (Weinmann et al. 2016). The nudge theory – originally derived from behavioral economics– is based on the irrational behavior of human beings. A nudge “is any aspect of the choice architecture that alters people’s behavior in a predictable way without forbidding any options or significantly changing their economic incentives” (Thaler and Sunstein 2008, p. 6) and is typically applied in offline environments, e.g., to nudge individuals for being organ donors through a default opt-in. By relying on the concept of nudging, individuals in digital work system could be nudged to improve their decisions when disclosing data. This is especially prevalent, since many individuals are not aware about how their data is used. As such, there is a lack of research regarding nudging in context of digital work systems and privacy which should be addressed in a socio-technical research approach. By examining the impact and perception of digital nudges in work systems, we want to shed light on the application, design and effects of nudges to overcome challenges that arise because of privacy related issues. We therefore first examine use cases and requirements for nudging in digital work system under the consideration of users, companies and other stakeholders. Since we draw on a socio-technical view, we incorporate requirements that relate to a legal as well as an ethical perspective for nudging privacy. By this means, we develop a design theory for privacy nudging by an iterative design and evaluation process in the field. The ultimate goal is to improve decisions concerning data disclosure and, secondary, increase by this means trust and acceptance of digital work systems by lowering privacy concerns. By developing a design theory, we contribute to the body of knowledge with a more profound understanding of digital nudging in the context of privacy as well as with prescriptive design knowledge for nudging in digital work systems.
Adaptive kNN Using Expected Accuracy for Classification of Geo-Spatial Data. Kibanov, Mark; Becker, Martin; Müller, Jürgen; Atzmueller, Martin; Hotho, Andreas; Stumme, Gerd. In Proc. 33rd ACM Symposium On Applied Computing. ACM Press, New York, NY, USA, 2018.
- [ BibSonomy-Post ]
A User-based Comparison of Two Augmented Reality Glasses. Klose, E. M.; Schmidt, L. In 25th IEEE Conference on Virtual Reality and 3D User Interfaces (Reutlingen 2018), K. Kiyokawa, F. Steinicke, B. Thomas, G. Welch (Hrsg.), S. 603–604. IEEE, Piscataway, 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
We present a scenario-based laboratory study with 40 participants comparing two augmented reality (AR) glasses in a travelling scenario. In a within-subject design, the binocular Epson Moverio BT-200 and the monocular Vuzix M100 were compared with regard to performance, acceptance, workload and preference. While performance was equal with both glasses, the Epson Moverio BT-200 glasses got higher acceptance and lower workload ratings and were preferred by the majority of the participants. The findings provide knowledge on human factors in AR glasses usage.
The What and How of Smart Personal Assistants: Principles and Application Domains for IS Research. Knote, Robin; Janson, Andreas; Eigenbrod, Laura; Söllner, Matthias. In Multikonferenz Wirtschaftsinformatik (MKWI). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Digitization brings new possibilities to ease our daily life activities by the means of assistive technology. Amazon Alexa, Microsoft Cortana, Samsung Bixby, to name only a few, heralded the age of smart personal assistants (SPAs), personified agents that combine artificial intelligence, machine learning, natural language processing and various actuation mechanisms to sense and influence the environment. However, SPA research seems to be highly fragmented among different disciplines, such as computer science, human-computer-interaction and information systems, which leads to ‘reinventing the wheel approaches’ and thus impede progress and conceptual clarity. In this paper, we present an exhaustive, integrative literature review to build a solid basis for future research. We have identified five functional principles and three research domains which appear promising for future research, especially in the information systems field. Hence, we contribute by providing a consolidated, integrated view on prior research and lay the foundation for an SPA classification scheme.
Towards a Pattern Language for Smart Personal Assistants. Knote, Robin; Söllner, Matthias; Leimeister, Jan Marco. In Conference on Pattern Languages of Programs (PLoP). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Supporting users in their daily activities, thus, making their lives more comfortable, has long been a goal for consumer-oriented systems development. With the rise of smart personal assistants (SPAs), however, we have reached a new milestone along the path towards this goal. These systems assist their owners by providing personalized and context-dependent information and service. Today's implementations reach from conversational agents, such as Siri, Cortana or Google Assistant, over chatbots, which are primarily text-based, to cognitive assistants, which assist according to a user's current cognitive or emotional state. However, although both research and practice proceed with full pace, recurring design elements of SPAs have not yet been investigated. We hence propose a pattern language for smart personal assistants to guide further empirical and design efforts. Therefore, we review existing information systems, computer science and human-computer interaction literature to find recurring design characteristics among 115 different assistants. The resulting pattern language contains 22 patterns that specify the interaction behavior and the intelligence of smart personal assistants.
The Other Human in The Loop -- A Pilot Study to Find Selection Strategies for Active Learning. Kottke, Daniel; Calma, Adrian; Huseljic, Denis; Sandrock, Christoph; Kachergis, George; Sick, Bernhard. In International Joint Conference on Neural Networks. Rio de Janiero, Brazil, 2018.
- [ BibSonomy-Post ]
Human Pose Estimation in Real Traffic Scenes. Kress, V.; Jung, J.; Zernetsch, S.; Doll, K.; Sick, B. In 2018 IEEE Symposium Series on Computational Intelligence (SSCI). Bangalore, India, 2018.
- [ BibSonomy-Post ]
Gestaltungsraum für proactive Smart Homes zur Gesundheitsförderung. Kromat, Theresa; Dehling, Tobias; Haux, Reinhold; Peters, Christoph; Sick, Bernhard; Tomforde, Sven; Wolf, Klaus-Hendrik; Sunyaev, Ali. In Multikonferenz Wirtschaftsinformatik. Lüneburg, Germany, 2018.
- [ BibSonomy-Post ]
Gestaltungsraum für proaktive Smart Homes zur Gesundheitsförderung. Kromat, Theresa; Dehling, Tobias; Haux, Reinhold; Peters, Christoph; Sick, Bernhard; Tomforde, Sven; Wolf, Klaus-Hendrik; Sunyaev, Ali. In Multikonferenz Wirtschaftsinformatik (MKWI). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Smart Homes sammeln eine Fülle von Daten über ihre Bewohner. Gut genutzt werden diese allerdings nicht. Smart Homes sind im wesentlichen reaktiv. Im Hinblick auf die Gesundheitsversorgung ist der Wandel zu proaktiven Smart Homes vielversprechend. Um proaktive Smart Homes Wirklichkeit werden zu lassen, sollte zunächst ein vollständiges Bild dieser komplexen und ressourcenreichen Umgebung gezeichnet werden. Das Ziel dieser Arbeit ist es, einen Gestaltungsraum für proaktive Smart Homes aufzuspannen. Ausgehend von den neun Elementen des Work System (WS) Rahmenwerks, werden Bausteine eines proaktiven Smart Homes identifiziert, beschrieben und analysiert sowie Gestaltungsfragen daraus abgeleitet, die bei einer Instanziierung eines proaktiven Smart Homes beantwortet werden müssen. Diese Arbeit bereitet einen fruchtbaren Nährboden für die zukünftige Gestaltung IT-gestützter proaktiver Lebenswelten, in denen die Gesundheit durch den Einsatz verschiedenster Systemressourcen proaktiv gefördert wird.
A service system modelling approach. Li, Mahei Manhai. In International Conference on Exporing Service Science (IESS). 2018.
- [ BibSonomy-Post ]
Reconceptualizing Service Systems – Introducing Service System Graphs. Li, Mahei Manhai; Peters, Christoph. In International Conference on Information Systems (ICIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Currently, research on service science has emerged as its own discipline, where service systems are its basic unit of analysis. However, without a clearly defined modeling approach for service systems, analyzing a service system is challenging. We therefore propose a conceptual hypergraph-based modeling approach, which can be used to model services for both traditional goods-dominant businesses, as well as service-businesses. We define key elements of a service system while drawing upon hypergraph theory and present three modeling properties which are required to model a service systems graph (SSG). The focus of SSGs is to describe the relationships between the various resources, actors and activities, thus configuring a service system. It provides the foundation for computer graphic simulations and database applications of service business structure for future research.
Towards Bridging the Gap between Business Model Innovation and Practice Using Hypergraph-based Modeling. Li, Mahei Manhai; Peters, Christoph; Ernst, Sissy-Josefina; Leimeister, Jan Marco. In INFORMS International Conference on Service Science (ICSS). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Dynamic Solutions in Service Systems. Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In AIS SIG SVC Pre-ICIS Workshop (Pre-ICIS). 2018.
- [ Abstract ]
- [ BibSonomy-Post ]
With the rapidly increasing number and complexity of service demands, service providers need to become even more flexible and faster. To accommodate this, the service system needs to dynamically reconfigure its required resourced based on the context of both service providers and the customer. The resulting chosen service system configuration is called a dynamic solution. Our research question is therefore as follow: How can we implement the characteristic of dynamic solutions based on the service system model (SSM)? We demonstrate our model using a real-life citizen-based produce delivery service. We contribute by being able to quantify service system configurations and compare different configurations dynamically. Keywords: Service operations, operationalizing
A Hypergraph-based Modeling Approach for Service Systems. Li, Mahei Manhai; Peters, Christoph; Leimeister, Jan Marco. In INFORMS International Conference on Service Science (ICSS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Currently, research on service science has emerged as its own discipline, where service systems are its basic unit of analysis. However, without a clearly defined modeling approach for service systems, analyzing a service system is challenging. We therefore propose a conceptual hypergraph-based modeling approach, which can be used to model services for both traditional goods-dominant businesses, as well as service-businesses. We define key elements of a service system while drawing upon hypergraph theory and present three modeling properties which are required to model a service systems graph (SSG). The focus of SSGs is to describe the relationships between the various resources, actors and activities, thus configuring a service system. It provides the foundation for computer graphic simulations and database applications of service business structure for future research.
Innovating Beyond the Fuzzy Front End: How to Use Reward-Based Crowdfunding to Co-create with Customers. Lipusch, Nikolaus; Dellermann, Dominik; Oeste-Reiß, Sarah; Ebel, Philipp. In Hawaii International Conference on System Sciences (HICSS), S. 4202–4211. 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Current research suggests that crowdfunding not only serves as an alternative source of capital but also as a flexible tool allowing start-ups to systematically integrate a crowd into their innovation processes. However, an adequate understanding of how start-ups can systematically leverage the co-creation potential of their early customers during crowdfunding is still nascent. Against this background, the aim of this research is to conceptualize and examine the concept of co-creation in the context of reward-based crowdfunding. In doing so, we distinguish it from other methods of user integration in the realm of open innovation and discuss how entrepreneurs can leverage reward-based crowdfunding to engage their customers in the development and deployment of their product and service offerings.
Geographically Distributed Deployment of Reproducible HRI Experiments in an Interdisciplinary Research Context. Lücking, Phillip; Lier, Florian; Bernotat, Jasmin; Wachsmuth, Sven; Ŝabanović, Selma; Eyssel, Friederike. In Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction, von HRI ’18, S. 181–182. ACM, Chicago, IL, USA, 2018.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
Reproducible experiments are a major requirement for transparent, comparable and verifiable results in the field of human-robot interaction (HRI). Furthermore, a version-controlled and well-structured "ready to deploy" system setup of soft- and hard-ware for an HRI experiment opens up a range of innovative possibilities for interdisciplinary efforts as well as simplified participation of collaborators in the research community. However, making experiments reproducible is not a trivial task. It stems from the lack of agreed upon methodologies, tools and the inherent technical complexity. In this work we present our latest efforts in the context of an international and interdisciplinary research project to enable robotics researchers, software engineers, and social scientists to work together to reproduce a behavioral HRI experiment. The successful reproduction demonstrates that our tool chain approach meets the proposed requirements of the reproducibility problem. To the best of our knowledge, this is the first time an integrated systemic approach allowed an identical instantiation of a complete HRI experiment at geographically distributed locations.
Digitale Wertschöpfung durch Crowd Services: Neue Formen des Kundensupports am Beispiel Mila und Swisscom. Mrass, Volkmar; Peters, Christoph. In Multikonferenz Wirtschaftsinformatik (MKWI). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Die digitale Transformation verändert gegenwärtig die Art und Weise, wie Arbeit erbracht und organisiert wird. Bestehende Geschäftsmodelle verlieren an Attraktivität, neue Geschäftsmodelle kommen hinzu. Zwei Trends sind dabei besonders signifikant: Die „Plattform-Ökonomie“, mit Crowdworking-Plattformen als einer ‚Spielart‘, die in den letzten Jahren starken Zulauf erfahren hat, und die „Sharing-Economy“. In diesem Beitrag zeigen wir am Beispiel der Crowdworking-Plattform Mila und ihres Kunden und 51-prozentigen Eigentümers Swisscom AG, wie Unternehmen die Crowd für Wertschöpfung einsetzen, ihren Kundensupport ausbauen und damit Vorteile für alle Beteiligten generieren können. Die Crowdworking-Plattform Mila verbindet in einem neuartigen Ansatz das Paradigma der Crowd, insbesondere die Nutzung einer Vielzahl von Leistungserbringern, mit den Prinzipien der Sharing-Economy, vor allem dem Einbezug der Kunden als Produzenten von Dienstleistungen. Basierend auf Experten-Tiefen-Interviews mit Verantwortlichen von Mila und Swisscom analysieren wir in diesem Beitrag dieses neuartige Arbeitssystem inklusive des Zusammenspiels aller Beteiligten und leiten daraus Handlungsempfehlungen für Unternehmen ab.
Managing Complex Work Systems via Crowdworking Platforms: How Deutsche Bank Explores AI Trends and the Future of Banking with Jovoto. Mrass, Volkmar; Peters, Christoph; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdsourcing has evolved into a powerful new instrument for companies. In the last years, crowdworking platforms that manage work systems as intermediaries between crowdsourcers and crowd workers have increasingly been used. Nevertheless, they currently often manage rather simple work systems. Although they have the potential for managing more complex ones, there is still little knowledge how this can be done and what measures are necessary to do so. To explore this question in more detail, we investigate three seminal projects that Deutsche Bank completed with the crowdworking platform Jovoto and that aimed at exploring AI trends and developing concepts for the future of banking. We derive measures necessary for the successful management of complex work systems and provide a model as guidance for both companies and crowdworking platform operators. With our findings, we extend current knowledge in the realm of IS, organizational theory, and platform ecosystems.
Managing Complex Work Systems via Crowdworking Platforms: How Intel and Hyve Explore Future Technological Innovations. Mrass, Volkmar; Peters, Christoph; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Crowdsourcing has the potential to change the way how companies and other organizations are working currently. Numerous companies are already exploiting this new form of work organization and are utilising the “wisdom of crowds”. Crowdworking platforms as intermediaries that manage the work system including customer companies and crowd workers play an important role in this context. Nevertheless, they currently mostly manage rather simple work systems that process rather plain work. In this summary for the HICSS 2018 Doctoral Consortium, we depict our current work in progress that aims at investigating how such platforms could also manage more complex work systems – a question that is crucial for the future success of this business model. Using the case of Intel and the crowdworking platform Hyve, we investigate one successful approach to tackle this challenge, elaborate on our method used as well as the theoretical background and communicate our first, preliminary findings.
Managing Complex Work Systems via Crowdworking Platforms: The Case of Hamburger Hochbahn and Phantominds. Mrass, Volkmar; Peters, Christoph; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
In the last decade, crowdsourcing has emerged as a new form of work organization. Crowdworking platforms as intermediaries between crowdsourcing companies and crowd workers have gained importance in this process. Currently, many of these platforms manage rather simple work systems. Using the case of the German Hamburger Hochbahn AG and the innovation platform Phantominds, this paper investigates measures necessary for crowdworking platforms to be able to manage also more complex work systems. To derive such measures, we analyze the work system of Hamburger Hochbahn and Phantominds, explore the interplay between the crowd and the platform provider and subsequently provide recommendations for companies that would like to use crowdworking platforms for the processing of work and for platform operators. With this paper, we extend current knowledge in the realms of IS, organizational theory, and platform ecosystems.
An automated pick-and-place benchmarking system in robotics. Neumann, N.; Meyer zu Borgsen, S.; Lücking, P.; Wachsmuth, S. In 2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), S. 243–249. 2018.
- [ Abstract ]
- [ URL ]
- [ DOI ]
- [ BibSonomy-Post ]
The reproducibility and objective assessment of a robot's manipulation ability is a crucial topic in robotics. The definition of testing protocols and the automation of such test procedures is challenging. Most evaluation protocols in benchmarks and competitions include not completely standardized interactions of a human/referee and are furthermore influenced by partially subjective criteria across different research areas. A promising and more objective solution is to automate benchmarking protocols for a range of reproducible manipulation tasks. We present an approach that is simplified to the essential elements, in which most of the process and evaluation is automated. The proposed system has low price and effort requirements and allows researchers to compare their robots without placing them side by side. To allow a wide range of robots to be benchmarked all parts will be available open source. In our system, an object is positioned in front of the benchmarked robot by a mobile minirobot that localizes itself on a table according to the individual task's predefined positions. By automating most of the process we ensure that the object locations tested as well as the timings are reproducible and well documented. This approach fosters the objective comparability of robot performances.
Formal Verification of ALICA Multi-agent Plans Using Model Checking. Nguyen Van, Thao; Fredivianus, Nugroho; Tran, Tam Huu; Geihs, Kurt; Binh Huynh, Thanh Thi. In Proceedings of the Ninth International Symposium on Information and Communication Technology. Danang City, Viet Nam, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Energy and Thriving. Professional Development Workshop on Energy. Ohly, Sandra. In Academy of Management Meeting. Chicago, 2018.
- [ BibSonomy-Post ]
Reasoning for Autonomous Agents in Dynamic Domains: Towards Automatic Satisfaction of the Module Property. Opfer, Stephan; Jakob, Stefan; Geihs, Kurt. In Agents and Artificial Intelligence, Bd. 1, S. 22–47. Springer International Publishing, 2018.
- [ BibSonomy-Post ]
Student Competition Teams: Combining Research and Teaching. Opfer, Stephan; Ossenkopf, Marie; Geihs, Kurt. In Proceedings of the 47th Annual Conference of the Southern African Computer Lecturers’ Association, SACLA 2018. Cape Town, South Africa, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Modular Service Structures for the Successful Design of Flexible Customer Journeys for AI Services and Business Models – Orchestration and Interplay of Services. Peters, Christoph; Zaki, Mohamed. In Working Paper Series of the Cambridge Service Alliance. Cambridge Service Alliance, University of Cambridge, Cambridge, UK, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure. Reitberger, G.; Zernetsch, S.; Bieshaar, M.; Sick, B.; Doll, K.; Fuchs, E. In ITSC. Maui, HI, 2018.
- [ BibSonomy-Post ]
Design and Evaluation of an IT-based Formative Feedback Tool to Foster Student Performance. Rietsche, Roman; Duss, Kevin; Persch, Jan Martin; Söllner, Matthias. In International Conference on Information Systems (ICIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Today’s world is changing faster than ever before. Students need to constantly acquire new knowledge and the required skills shift more and more to higher order thinking skills. One major approach to support the students in this shift is through formative feedback, which initiates self-regulated learning processes. However, given the constant rise of student numbers while public spending remains constant, one of the major challenges is how to effectively provide formative feedback in large-scale lectures. The aim of our project is to develop an IT-tool which provides students with formative feedback to increase their performance in large-scale lectures. Our results show that through the use of the IT-tool the objective and perceived student performance can be significantly increased. By documenting our design knowledge according to the eight components of Gregor and Jones (2007), we take a first step towards creating a design theory for formative feedback tools.
Radar-based Feature Design and Multiclass Classification for Road User Recognition. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In 2018 IEEE Intelligent Vehicles Symposium (IV), S. 779–786. IEEE, Changshu, China, 2018.
- [ BibSonomy-Post ]
Generalizing Application Agnostic Remaining Useful Life Estimation Using Data-Driven Open Source Algorithms. Schlegel, B.; Mrowca, A.; Wolf, P.; Sick, B.; Steinhorst, S. In IEEE 3rd International Conference on Big Data Analysis. Shanghai, China, 2018.
- [ BibSonomy-Post ]
Prominence and Dominance in Networks. Schmidt, Andreas; Stumme, Gerd. In Proceedings of the 21th International Conference on Knowledge Engineering and Knowledge Management (EKAW), von Lecture Notes in Computer Science, C. Faron Zucker, C. Ghidini, A. Napoli, T. Yannick (Hrsg.), S. 370–385. Springer, 2018.
- [ BibSonomy-Post ]
Understanding the Effects of Gamified Feedback in Mobile Learning – An Experimental Investigation. Schneider, Tim; Janson, Andreas; Schöbel, Sofia. In International Conference on Information Systems (ICIS). San Francisco, California, USA, 2018.
- [ BibSonomy-Post ]
Avatar Designs are in the Eye of the Beholder – About Identifying Preferred Avatar Designs in Digital Learning. Schöbel, Sofia; Janson, Andreas. In Annual Pre-ICIS Workshop on HCI Research in MIS (Pre-ICIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Gamification focuses on using game-like elements in non-entertainment-based contexts. An example for a game element is an avatar. Although lots of research has focused on analyzing avatars in gamification, little is known about which kind of avatar design users prefer. Especially avatars in gamification that are used as tutors or mentors for learning purposes do not spark the interest of users. Thus, the goal of our paper is to analyze the kinds of avatar designs users of digital learning environments such as learning management systems would prefer. For that purpose, we use a best-worst scaling approach to analyze if the familiarity and shape of avatars determine user preferences in gamification. Our research will contribute to research and practice as it delivers implications about how to design avatars in gamified learning systems. We will enrich theory by getting a better understanding about the general meaning of user-centered avatar designs in gamification.
Gamifying Information Systems - Improving Motivation and Effective Use Through a Theory-motivated Method. Schöbel, Sofia; Janson, Andreas. In International Conference on Information Systems (ICIS). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Is it all about Having Fun? - Developing a Taxonomy to Gamify Information Systems. Schöbel, Sofia; Janson, Andreas. In European Conference on Information Systems (ECIS). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Gamification is a well-known approach that refers to the use of game design elements in information systems to make monotonous and tedious tasks more enjoyable. However, research and practice show that game design elements are oftentimes chosen and integrated in information systems randomly, therefore impeding the outcomes of such systems. In this regard, taxonomies can guide system developers, i.e., in selecting and combining game design elements to gamify their information system. Nonetheless, existing taxonomies do not provide such guidance for gamifying information systems. Therefore, the goal of our research is to consolidate the state of the art of gamification research and rigorously develop a gamification taxonomy. To achieve our goal, we conducted a systematic literature review and developed a taxonomy based on a rigorous taxonomy development process. We evaluate our theory by providing evidence of its feasibility with two practical cases: First, we show how the taxonomy helps to analyze existing gamification approaches, and, second, how the taxonomy guides to gamify information systems. Overall, we enrich theory by introducing a new taxonomy to better explain the meaning and characteristics of game design elements. Likewise, practitioners will be guided in selecting and combining game design elements for their gamification approaches.
Quantifying the Influences on Probabilistic Wind Power Forecasts. Schreiber, Jens; Sick, Bernhard. In International Conference on Power and Renewable Energy, Bd. 3, S. 6. 2018.
- [ Abstract ]
- [ BibSonomy-Post ]
In recent years, probabilistic forecasts techniques were proposed in research as well as in applications to integrate volatile renewable energy resources into the electrical grid. These techniques allow decision makers to take the uncertainty of the prediction into account and, therefore, to devise optimal decisions, e.g., related to costs and risks in the electrical grid. However, it was yet not studied how the input, such as numerical weather predictions, affects the model output of forecasting models in detail. Therefore, we examine the potential influences with techniques from the field of sensitivity analysis on three different black-box models to obtain insights into differences and similarities of these probabilistic models. The analysis shows a considerable number of potential influences in those models depending on, e.g., the predicted probability and the type of model. These effects motivate the need to take various influences into account when models are tested, analyzed, or compared. Nevertheless, results of the sensitivity analysis will allow us to select a model with advantages in the practical application.
How to Design a Crowdwork Platform. Schuster, Johannes; Dellermann, Dominik; Lipusch, Nikolaus; Kohler, Thomas. In Social Science Research Network (SSRN). 2018.
- [ URL ]
- [ BibSonomy-Post ]
Machines as Teammates: A Collaboration Research Agenda. Seeber, Isabella; Bittner, Eva; Briggs, Robert O.; De Vreede, Gert-Jan; De Vreede, Triparna; Druckenmiller, Douglas; Maier, Ronald; Merz, Alexander B.; Oeste-Reiß, Sarah; Randrup, Nils; Schwabe, Gerhard; Söllner, Matthias. In Hawaii International Conference on System Sciences (HICSS), S. 420–429. 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Humans will soon need to adapt to a collaborative setting in which technology becomes a smart collaboration partner that works with a group to achieve its goals. It is therefore time for collaboration researchers to explore the vast opportunities afforded by smart technology and to test its utility for enhancing team processes and outcomes. In this paper, we take a long view on the implications of smart technology for collaboration process design, and propose a research agenda for the next decade of collaboration research. We create a reference model to frame the research agenda.
Reduzieren Unterbrechungen die Arbeitsleistung? Ein experimenteller Vergleich selbst- und fremdbestimmter Unterbrechungen. Seipp, Ann-Kathrin; Heißler, Clara; Ohly, Sandra. In Presentation at the 51. Kongress der deutschen Gesellschaft für Psychologie (DGPs) in Frankfurt. 2018.
- [ BibSonomy-Post ]
Energy at work: A Meta-Analytic Approach to Human Energy Conceptualization and Work-Related Concepts. Seipp, Ann-Kathrin; Schmitt, Antje; Ohly, Sandra. In Poster presentation at the 13th European Academy of Occupational Health Psychology Conference, Lisbon, K. Teoh, N. Saade, V. Dediu, J. Hassard, L. Torres (Hrsg.), S. 446. 2018.
- [ BibSonomy-Post ]
KoLeArn – Smarte und kontextsensitive Aus- und Weiterbildung für die chinesische Industrie. Thiel de Gafenco, Marian; Janson, Andreas; Schneider, Tim. In Die 16. E-Learning Fachtagung Informatik (DeLFI), Lecture Notes in Informatics (LNI), D. Krömker, U. Schroeder (Hrsg.), S. 281–282. Frankfurt am Main, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Anforderungs- und Entwurfsmuster als Instrumente des Privacy by Design. Thies, Laura F.; Knote, Robin; Jandt, Silke; Söllner, Matthias; Roßnagel, Alexander; Leimeister, Jan Marco. In Die Fortentwicklung des Datenschutzes. DuD-Fachbeiträge, A. Roßnagel, M. Hansen, M. Friedewald (Hrsg.), S. 175–191. Springer Vieweg, Wiesbaden, Germany, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Towards Proactive Health-enabling Living Environments : Simulation-based Study and Research Challenges. Tomforde, Sven; Dehling, Tobias; Haux, Reinhold; Huseljic, Denis; Kottke, Daniel; Scheerbaum, Jonas; Sick, Bernhard; Sunyaev, Ali; Wolf, Klaus-Hendrik. In ARCS Workshop 2018, 31th International Conference on Architecture of Computing Systems, S. 1–8. VDE, 2018.
- [ BibSonomy-Post ]
DECOM: A framework to support evolution of IoT services. Tran, Tam Huu; Jahl, Alexander; Geihs, Kurt; Kuppili, Ramaprasad; Nguyen, Thang Xuan; Binh Huynh, Thanh Thi. In Proceedings of the Ninth International Symposium on Information and Communication Technology. Danang City, Viet Nam, 2018.
- [ URL ]
- [ BibSonomy-Post ]
Unleashing the Potential of Chatbots in Education: A State-Of-The-Art Analysis. Winkler, Rainer; Söllner, Matthias. In Academy of Management Annual Meeting (AOM). 2018.
- [ Abstract ]
- [ URL ]
- [ BibSonomy-Post ]
Chatbots are becoming a ubiquitous trend in many fields such as medicine, product and service industry, and education. Chatbots are computer programs used to conduct auditory or textual conversations. A growing body of evidence suggests that these programs have the potential to change the way students learn and search for information. Especially in large-scale learning scenarios with more than 100 students per lecturer, chatbots are able to solve the problem of individual student support. However, until now, there has been no systematic, structured overview of their use in education. The aim of this paper is therefore to conduct a systematic literature review based on a multi-perspective framework, from which we have derived initial search questions, synthesized past research, and highlighted future research directions. We reviewed titles and abstracts of 1405 articles drawn from management, education, information systems, and psychology literature before examining and individually coding a relevant subset of 80 articles. The results show that chatbots are in the very beginning of entering education. Few studies suggest the potential of chatbots for improving learning processes and outcomes. Nevertheless, past research has revealed that the effectiveness of chatbots in education is complex and depends on a variety of factors. With our literature review, we make two principal contributions: first, we structure and synthesize past research by using an input-process-output framework, and secondly, we use the framework to highlight research gaps for guiding future research in that area.
Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network. Zernetsch, Stefan; Kress, Viktor; Sick, Bernhard; Doll, Konrad. In 2018 IEEE Intelligent Vehicles Symposium, IV 2018, Changshu, Suzhou, China, June 26-30, 2018, S. 1–6. 2018.
- [ BibSonomy-Post ]

2017[ to top ]

Exceptional Model Mining in Ubiquitous and Social Environments. Atzmueller, Martin. In Proc. Annual Machine Learning Conference of the Benelux (Benelearn 2017). Eindhoven University of Technology, Eindhoven, The Netherlands, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Onto Explicative Data Mining: Exploratory, Interpretable and Explainable Analysis. Atzmueller, Martin. In Proc. Dutch-Belgian Database Day. TU Eindhoven, Netherlands, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Anomaly Analytics and Structural Assessment in Process Industries. Atzmueller, Martin; Arnu, David; Schmidt, Andreas. In Proc. Annual Machine Learning Conference of the Benelux (Benelearn 2017). Eindhoven University of Technology, Eindhoven, The Netherlands, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Anomaly Detection and Structural Analysis in Industrial Production Environments. Atzmueller, Martin; Arnu, David; Schmidt, Andreas. In Proc. International Data Science Conference (IDSC 2017). Salzburg, Austria, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Explanation-Aware Feature Selection using Symbolic Time Series Abstraction: Approaches and Experiences in a Petro-Chemical Production Context. Atzmueller, Martin; Hayat, Naveed; Schmidt, Andreas; Klöpper, Benjamin. In Proc. IEEE International Conference on Industrial Informatics (INDIN). IEEE Press, Boston, MA, USA, 2017.
- [ URL ]
- [ BibSonomy-Post ]
HypGraphs: An Approach for Analysis and Assessment of Graph-Based and Sequential Hypotheses. Atzmueller, Martin; Schmidt, Andreas; Kloepper, Benjamin; Arnu, David. In New Frontiers in Mining Complex Patterns. Postproceedings NFMCP 2016, Bd. 10312 von LNAI. Springer Verlag, Berlin/Heidelberg, Germany, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Mixed-Initiative Feature Engineering Using Knowledge Graphs. Atzmueller, Martin; Sternberg, Eric. In Proc. 9th International Conference on Knowledge Capture (K-CAP). ACM Press, New York, NY, USA, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Contact Patterns, Group Interaction and Dynamics on Socio-Behavioral Multiplex Networks. Atzmueller, Martin; Thiele, Lisa; Stumme, Gerd; Kauffeld, Simone. In Proc. Annual Machine Learning Conference of the Benelux (Benelearn 2017). Eindhoven University of Technology, Eindhoven, The Netherlands, 2017.
- [ URL ]
- [ BibSonomy-Post ]
Improving Smartphone Based Collision Avoidance by Using Pedestrian Context Information. Bachmann, M.; Morold, M.; David, K. In Proceedings of the 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom {Workshops}), S. 2–5. IEEE, Kona, HI, USA, 2017.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
Pedestrians globally comprise 22 % of all road traffic deaths in 2013. Various approaches for reducing accident numbers have already been introduced and are still being researched. Most of these approaches have specific limitations, like requiring line of sight. To overcome these limitations, we propose the Wireless Seat Belt (WSB), a smartphone-based collision avoidance system for pedestrians. Unlike other systems, the WSB uses context information, obtained from a pedestrian's smartphone, not only as additional information but also for using the information to improve the collision detection accuracy. The WSB introduces independent, individual modules for recognizing the pedestrian's direction, position, and speed. We first evaluate the influence of the measurement errors of each module on the missed alarm probability in a typical urban collision scenario using a simulator. Then, the impact of using the pedestrian's context to decrease the missed alarm probability is evaluated. The evaluation is done using the example of a curb detection module. The curb detection is used to infer that the pedestrian has stepped onto the street to correct the pedestrian's position. The results show a decrease of the missed alarm probability by 46.5 % in the scenario considered.
On the Usability of Probably Approximately Correct Implication Bases. Borchmann, Daniel; Hanika, Tom; Obiedkov, Sergei. In Formal Concept Analysis - 14th International Conference, ICFCA 2017, Rennes, France, June 13-16, 2017, Proceedings, Bd. 10308 von Lecture Notes in Computer Science, K. Bertet, D. Borchmann, P. Cellier, S. Ferré (Hrsg.), S. 72–88. Springer, 2017.
- [ URL ]
- [ DOI ]
- [