Mensch und Computer 2023
Mensch und Computer 2023 vom 3.-6. September 2023 in Rapperswil, Schweiz
Auflistung nach:
Auflistung Mensch und Computer 2023 nach Erscheinungsdatum
1 - 10 von 205
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragTrainOn: An Open Source Plugin for Developing Online Trainings and Conducting Studies in WordPress TrainOn: Ein Open Source-Plugin für die Entwicklung von Online-Trainings und Durchführung von Studien in WordPress(Mensch und Computer 2023 - Tagungsband, 2023) Mallwitz, Tim; Janneck, Monique; Sternitzke, Max; Mergan, HamidWeb-based platforms do not always offer the necessary prerequisites for the development and scientific monitoring of online interventions. Also, the use of these platforms is often associated with high licensing fees. This article presents TrainOn, an open source plugin for WordPress that can be used to create complex interactive online trainings as well as to realize online surveys and complex study designs.Webbasierte Plattformen bieten nicht immer die notwendigen Voraussetzungen zur Entwicklung und wissenschaftlichen Begleitung von Online-Interventionen. Auch ist die Nutzung dieser Plattformen häufig mit hohen Lizenzgebühren verbunden. Dieser Beitrag stellt TrainOn vor, ein Open Source-Plugin für WordPress, mit dem komplexe interaktive Online-Trainings erstellt sowie Online-Befragungen und komplexe Studiendesigns realisiert werden können.
- KonferenzbeitragMobile AR in the Wild: Exploring an Augmented Reality Concept for a Nature Discovery Path and evaluating its Serious Game Elements(Mensch und Computer 2023 - Tagungsband, 2023) Trefzger, Mathias; Schlegel, ThomasThis short paper presents the concept for an Augmented Reality (AR) nature trail application aimed at enhancing the user's experience and interaction with the natural environment. The app leverages the capabilities of modern smartphones and AR technology to overlay digital elements onto the real world, providing users with an immersive and educational experience. The research focuses on evaluating the concept and the app prototype itself with its different elements and games. A main goal of the app is to appeal to a teenage target group in order to interest them in visiting the nature discovery trail. Our results show that they enjoy using the app when being on site as part of a school trip for example. But for most teenage participants it is unlikely to visit the nature trail in their free time because of the app. The study serves as a first step to gather an overall concept how the different app elements are perceived. Initial findings indicate that different user groups have preferences relating the app elements and games. For example, the above average tech-savvy participants in our experiment rated the implemented quiz significantly better than the below average tech-savvy group. The paper also presents the subjective assessment of the participants how much they learned with the app, if they thought the app to be distracting them from the surroundings and more. The paper also highlights some challenges encountered during the development process and outlines future directions for improvement and expansion. Overall, this study presents an encouraging glimpse into the potential of AR technology to enhance nature experiences and promote environmental education.
- KonferenzbeitragBehind the Screens: Exploring Eye Movement Visualization to Optimize Online Teaching and Learning(Mensch und Computer 2023 - Tagungsband, 2023) Sauter, Marian; Wagner, Tobias; Hirzle, Teresa; Lin, Bao Xin; Rukzio, Enrico; Huckauf, AnkeThe effective delivery of e-learning relies on the continuous monitoring and management of students' attention. While instructors in traditional classroom settings can readily assess crowd attention through gaze cues, these cues are largely unavailable in online learning environments. To address this challenge and highlight the significance of our study, we collected eye movement data from twenty students and developed four visualization methods: (a) a heat map, (b) an ellipse map, (c) two moving bars, and (d) one vertical bar, which were overlaid on 13 instructional videos. Our findings revealed unexpected preferences among instructors. Contrary to expectations, they did not favor the established heat map and vertical bar for live online teaching. Instead, they opted for the less intrusive ellipse visualization. Despite this, the heat map remained the preferred choice for retrospective analyses due to its more detailed information. Importantly, all visualizations were deemed useful and contributed to re-establishing emotional connections in online learning. In conclusion, our innovative visualizations of crowd attention demonstrate considerable potential for a broad range of applications, extending beyond e-learning to encompass all online presentations and retrospective analyses. The significant outcomes of our study underscore the crucial role these visualizations will play in enhancing both the effectiveness and emotional connectedness of future e-learning experiences, thereby facilitating the educational landscape.
- KonferenzbeitragApplying a Feature-Oriented Software Development Approach to Model Interaction Diversity(Mensch und Computer 2023 - Tagungsband, 2023) David, Gollasch; Gerhard, WeberThis research introduces a novel modelling approach based on methods from feature-oriented software development, aimed at enhancing accessibility and diversity in interactive systems. The method integrates user requirements, particularly accessibility and sensitivity to diversity, into software family development. Utilizing a user model subtree, it allows for customization based on users' needs, constraints, and preferences. A prototypical demonstration is shown through a voice user interface of an assistance robot. Despite an overall satisfying success rate of 96%, results suggest the quality of configuration slightly decreases with an increasing number of user constraints. This innovative approach offers significant potential, especially given the growing need for personalized human-computer interaction in our ageing society. However, it also prompts further research questions, such as its adaptability to non-software family systems and quality of configuration via smart AI models.
- KonferenzbeitragAI said, She said - How Users Perceive Consumer Scoring in Practice(Mensch und Computer 2023 - Tagungsband, 2023) Recki, Lena; Esau-Held, Margarita; Lawo, Dennis; Stevens, GunnarAs digitization continues, consumers are increasingly exposed to AI’s scoring decisions. However, we lack a thorough understanding of how users' misjudgments lead to a rejection of the system. Therefore, we must investigate the appropriation of such socio-technical systems in practice and how users describe their experience with algorithm-based scoring. To address this issue, we evaluated 1003 user reviews of an app of car insurance that calculates its premium based on the consumers' individual driving behavior. We find evidence that users develop their own folk theories to explain the algorithms with the help of situation-related experiences and that insufficient explanations lead to power asymmetries between consumers, the system, and the company. In particular, we uncover a fundamental conflict between computational risk assessment and the perceived agency to influence the score as a result of the different needs of the stakeholders involved.
- KonferenzbeitragHoloBoard: A gamified balance board experience(Mensch und Computer 2023 - Tagungsband, 2023) Frölke, Robin; Benjamin, Butz; Lux, Gregor; Gerken, JensIn this demo, we present HoloBoard, a HoloLens2-based Augmented Reality application, which gamifies traditional balance board training to make it more engaging and enjoyable. Ankle injuries are among the most common injuries in many ball sports. Balance training, such as training programs which use a balance board, can help stabilize foot joints and prevent injuries. Traditional balance training is often inadequate because there is no feedback, and the "monotonous" movements are perceived as "boring". Our application is based on the Unreal game engine and utilizes the HoloLens2 to engage the player in various ball sports related game types such as catching, heading and dodging, thereby requiring various body movements similar to traditional balance board training programs.
- KonferenzbeitragFrom ChatGPT to FactGPT: A Participatory Design Study to Mitigate the Effects of Large Language Model Hallucinations on Users(Mensch und Computer 2023 - Tagungsband, 2023) Leiser, Florian; Eckhardt, Sven; Knaeble, Merlin; Maedche, Alexander; Schwabe, Gerhard; Sunyaev, AliLarge language models (LLMs) like ChatGPT recently gained interest across all walks of life with their human-like quality in textual responses. Despite their success in research, healthcare, or education, LLMs frequently include incorrect information, called hallucinations, in their responses. These hallucinations could influence users to trust fake news or change their general beliefs. Therefore, we investigate mitigation strategies desired by users to enable identification of LLM hallucinations. To achieve this goal, we conduct a participatory design study where everyday users design interface features which are then assessed for their feasibility by machine learning (ML) experts. We find that many of the desired features are well-perceived by ML experts but are also considered as difficult to implement. Finally, we provide a list of desired features that should serve as a basis for mitigating the effect of LLM hallucinations on users.
- KonferenzbeitragAppealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making(Mensch und Computer 2023 - Tagungsband, 2023) Ammeling, Jonas; Manger, Carina; Kwaka, Elias; Krügel, Sebastian; Uhl, Matthias; Kießig, Angelika; Fritz, Alexis; Ganz, Jonathan; Riener, Andreas; Bertram, Christof A.; Breininger, Katharina; Aubreville, MarcArtificial intelligence (AI)-based recommender systems can help to improve efficiency and accuracy in medical decision making. Yet, it has been shown that a recommendation given by an algorithm can influence the human expert responsible for the decision. The strength and direction of this bias, induced by a computer-aided diagnosis workflow, can be influenced by the visual representation of the results. This study focuses on evaluating four frequently used visualization types (bounding box, segmentation mask, segmentation contour, and heatmap) for displaying segmentation results of medical data. A group of 24 medical experts specializing in pathology and radiology participated in the evaluation, assessing the subjective appeal of these visualizations. The study evaluated the pragmatic and hedonic quality of the visualizations based on a standardized questionnaire and specific criteria relevant to medical decision making. The findings indicate that the heatmap received the highest ratings for non-task-oriented aspects of the user experience. However, it exhibited significant inconsistencies among experts concerning task-oriented aspects and was perceived as the most biasing visualization type. On the other hand, the segmentation contour consistently received high ratings across various subscales. The results of the study contribute to better alignment between visualization techniques and user requirements for the development of future AI-based recommender systems.
- KonferenzbeitragKnowing the Limits – Human-Centered Explanations of Functionality and Limits of AI(Mensch und Computer 2023 - Tagungsband, 2023) Graichen, Lisa; Graichen, MatthiasBuilding an appropriate mental model about the functional principles and limitations of technical systems or AI-based applications is crucial, particularly when these systems are applied in domains involving high risk to user safety, like driving. The presented paper describes an upcoming study on applying methods from Explainable AI to facilitate the building of mental models and investigate their effects on user trust. For the interaction with an AI-based system, we use an algorithm designed to support drivers at intersections by predicting turning maneuvers, thus being able to warn a driver of potential cyclists when turning right. Participants will be able to experience the system in a simulated driving environment. We will investigate the effect of receiving comprehensive training about the system's functionality and limitations on mental models, trust, and acceptance.
- KonferenzbeitragInvestigating Visual Countermeasures Against Dark Patterns in User Interfaces(Mensch und Computer 2023 - Tagungsband, 2023) Schäfer, René; Miles, Paul; Preuschoff; Jan, BorchersDark patterns are malicious interface design strategies on the web and in apps that trick users into decisions that go against their best interests, costing them money, time, or private data. While there are approaches to classifying these patterns and investigating user awareness, there has been little work looking into visual countermeasures against dark patterns. In this work, we used an online survey to investigate concepts for six visual countermeasures against three common dark patterns: Confirmshaming, Low-stock Message, and Visual Interference. Our results indicate two opposing forces for users: On the one hand, users dislike systems actively making silent changes to their screen, preferring to be informed about the presence of dark patterns. On the other hand, they do not want applications to become visually cluttered, as this may impact their productivity. We found that different applications of dark patterns require different countermeasures, and that individual preferences vary strongly.