Logo des Repositoriums

Auflistung nach Autor:in "Baldauf, Matthias"

1 - 10 von 78
  • Konferenzbeitrag
    3, 2, 1 Start with Breastfeeding: Supporting Partner Involvement in Breastfeeding Education Through a Gamified Mobile App
    (Mensch und Computer 2023 - Tagungsband, 2023) Tang, Kymeng; Kathrin, Gerling; Lijnen, Marnix; Geets, Marten; Geurts, Luc; Aufheimer, Maria; Muyldermans, Joke
    Interactive technology offers a unique opportunity to supplement breastfeeding education, engaging expecting parents in reflection on breastfeeding. Yet, interventions typically target mothers, and although partner support is an important predictor of breastfeeding success, it is rarely addressed in interventions. We present 3, 2, 1 Start with Breastfeeding, a gamified mobile app that allows users to take care of a virtual baby alone or with their partner while engaging with educational content. The app was designed off an existing breastfeeding intervention, and leverages Self-Determination Theory to address parents and their partners. An evaluation with twelve parents show that the app engaged parents and their partners, and successfully communicated the lived experience of early-stage breastfeeding. However, our results also suggest that involving partners needs to be done with nuance to emphasise autonomy. We discuss these findings to derive considerations for the design of interactive interventions to support breastfeeding.
  • Konferenzbeitrag
    A user-centred approach to facilitate locating company security policies; Nutzerzentrierter Ansatz zur Vereinfachung des Auffindens von Security Policies
    (Mensch und Computer 2023 - Tagungsband, 2023) Aldag, Lukas; Ballreich, Fabian; Berens, Benjamin; Volkamer, Melanie
    English: An important factor for the effectiveness of security awareness measures in companies is awareness and consistency of security policies. As part of a case study, a document was created using a user-centred approach that gives an overview of all relevant individual documents (so-called overview document). In addition, a process for publication was developed and evaluated iteratively. The case study took place at a medium-sized energy company in Germany. General lessons learned are derived from the case study. For example, distributing important documents via e-mail carries the risk that this is perceived as less important or is not perceived at all. Deutsch: Ein wichtiger Faktor für die Effektivität von Security Awareness-Maßnahmen in Unternehmen sind die Bekanntheit und Konsistenz von Security Policies. Im Rahmen einer Case Study wurde mit einem nutzerzentrierten Ansatz ein Dokument, das den Nutzenden eine Übersicht über alle relevanten Einzeldokumente (sog. Übersichtsdokument) gibt und ein Prozess zur Bekanntmachung iterativ entwickelt und evaluiert. Die Case Study fand bei einem mittelgroßen Energieversorgungsunternehmen in Deutschland statt. Aus der Case Study werden allgemeine Lessons Learned abgeleitet. Beispielsweise birgt eine Verteilung von wichtigen Dokumenten über E-Mail die Gefahr, dass diese gar nicht oder als weniger wichtig wahrgenommen wird.
  • Konferenzbeitrag
    Accessible Text Tools for People with Cognitive Impairments and Non-Native Readers: Challenges and Opportunities
    (Mensch und Computer 2023 - Tagungsband, 2023) Heuer, Hendrik; Glassman, Elena Leah
    Many people have problems with reading, which limits their ability to participate in society. This paper explores tools that make text more accessible. For this, we interviewed experts, who proposed tools for different stakeholders and scenarios. Important stakeholders of such tools are people with cognitive impairments and non-native readers. Frequently mentioned scenarios are public administration, the medical domain, and everyday life. The tools proposed by experts support stakeholders by improving how text is compressed, expanded, reviewed, and experienced. In a survey of stakeholders, we confirm that the scenarios are relevant and that the proposed tools appear helpful to them. We provide the Accessible Text Framework to help researchers understand how the different tools can be combined and discuss how individual tools can be implemented. The investigation shows that accessible text tools are an important HCI+AI challenge that a large number of people can benefit from.
  • Konferenzbeitrag
    AI said, She said - How Users Perceive Consumer Scoring in Practice
    (Mensch und Computer 2023 - Tagungsband, 2023) Recki, Lena; Esau-Held, Margarita; Lawo, Dennis; Stevens, Gunnar
    As 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.
  • Konferenzbeitrag
    Alexa, It’s Me! An Online Survey on the User Experience of Smart Speaker Authentication
    (Mensch und Computer 2022 - Tagungsband, 2022) Renz, Andreas; Baldauf, Matthias; Maier, Edith; Alt, Florian
    Verifying the identify of the speaker is a crucial requirement for security-critical voice-based services on smart speakers, such as transferring money or making online purchases. Whilst various studies have explored novel authentication mechanisms for voice based services, there is little research on the user experience of respective authentication methods. To address this gap, we conducted a comprehensive online survey (n=696). We compared five authentication methods (spoken PIN, biometrics, app with button/voice confirmation, card reader) regarding their perceived efficiency, security, ease of use, and error susceptibility. Additionally, we investigated users’ willingness to use security-critical services in banking and government. We found an overall preference to confirm actions triggered by voice by pressing a button on a mobile authentication app followed by PIN-based authentication. In contrast, biometric authentication by voice is considered unreliable, while applying a card reader is regarded secure, yet less convenient.
  • Konferenzbeitrag
    Appealing 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, Marc
    Artificial 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.
  • Konferenzbeitrag
    Applying a Feature-Oriented Software Development Approach to Model Interaction Diversity
    (Mensch und Computer 2023 - Tagungsband, 2023) David, Gollasch; Gerhard, Weber
    This 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.
  • Konferenzbeitrag
    ARchi VR: Real-time Collaboration in Augmented Spaces
    (Mensch und Computer 2023 - Tagungsband, 2023) Santiago, Moreno; Philipp, Ackermann
    This paper showcases the integration of real-time collaboration features for handheld AR devices used in indoor environments. The implemented collaboration functionality enables participants in a shared AR session to create and edit virtual objects by supporting remote, multi-modal visualization and interaction in 2D, 3D and AR. Additionally, we demonstrate our ongoing efforts in exploring video-based interaction with remote AR scenes. The implemented communication architecture and feature set was developed for Apple iOS devices based on the existing general-purpose room-scanning app ARchi VR. The prototype application demonstrates the feasibility and the potential of multi-modal collaboration in AR.
  • Konferenzbeitrag
    Assistance in Virtual Reality Exergames: Preference for Species of Agents in Relation to Personality of Users
    (Mensch und Computer 2023 - Tagungsband, 2023) Lehmann, Nora; Kruse, Lucie; Steinicke, Frank
    Virtual agents (VAs) can be used in a variety of scenarios, e.g. as assistants or in exergame tutorials. One of the advantages of VAs is that they can be customized to the user’s needs. Still, little research is done on preferences for the appearance of agents, especially when user groups are of mixed age. This work explores the effect of the species (abstract, animal, and human) of the agent on several dependent variables: user experience, anthropomorphism, animacy, likeability, and perceived intelligence. Therefore, an experimental study with a within-subject design was conducted. Furthermore, the effect of the user’s personality on the perception was investigated. Main findings were that people that had a high score in the openness to new experiences trait rated embodied agents significantly higher in likeability and animacy than people with a low score. This work highlights the importance of tailoring the appearance of agents to the users.
  • Zeitschriftenartikel
    Authentication methods for voice services on smart speakers – a multi-method study on perceived security and ease of use
    (i-com: Vol. 22, No. 1, 2023) Renz, Andreas; Neff, Thomas; Baldauf, Matthias; Maier, Edith
    With the increasing proliferation of security-critical voice-based services such as voice banking, user authentication on smart speakers is becoming a vital requirement. Prior research on verifying the speaker’s identity has been taken a technical perspective predominantly, while respective user-centered research is scarce. To investigate authentication methods for smart speakers from a user’s perspective, we conducted a multi-method experiment. In a comprehensive online survey (n = 696) and a comparative lab study (n = 18) with an advanced functional prototype we studied 6 authentication methods (spoken PIN, biometrics, app with button/voice confirmation, card reader, sound authentication) regarding their perceived security and ease of use. While token-based authentication approaches (in particular an authenticator app on a smartphone) typically are perceived as more secure, they are found inferior when it comes to the ease of use. The currently most frequently used authentication method for smart speakers, the spoken PIN method, seems to represent a compromise between security and ease of use. The sophisticated sound authentication was appreciated for its ease of use, however, was rated worst regarding the perceived security.