Refine
Document Type
Has Fulltext
- no (22)
Reviewed
- Begutachtet/Reviewed (16)
Keywords
- Affective Computing, User Experience (UX), UX Design, Emotion (1)
- GDPR; usable privacy; empirical study; right to information (1)
- data set, artificial intelligence, emotion recognition, user interaction (1)
- dataset (1)
- qualitative sociological research, human-centered design, homelessness, design thinking (1)
- usability; UX; virtual prototypes; AR; VR; MR; XR; technical devices; home appliances (1)
- user emotions (1)
- user experience (1)
- user interactions (1)
Institute
Social media usage has greatly increased during the pandemic. The use of social media has been linked to mental health consequences. Especially TikTok is under scrutiny because of its captivating UX Design as well as controversial privacy policies. This study shows how Mobile Affective Computing Research can reliably and objectively measure the implicit-emotional UX. The results suggest that TikTok triggers positive emotions during onboarding and strengthens the emotional bond with increasing usage - mainly due to the personalization algorithm. In particular, the study further reveals that there are no clear relationships when “only self-reported data” is used to understand app usage behavior. However, emotion data based on facial coding shows that TikTok users get emotionally aroused. Initially, a positive and relaxed mood triggers further usage time, while - counter-intuitively - later sessions result in an increasingly negative and aroused mood. However, people are largely unaware of these relationships when questioned. Thus, implicit measures, such as facial coding, may help identify valid social media usage reactions. These results yield implications that call for political regulation considering aspects of social media apps and user behavior.
Bei der Entwicklung von technischen Geräten sollte deren Nutzerschnittstelle bereits auf der Ebene virtueller Prototypen evaluiert werden. Dafür bieten sich realitätsnahe Darstellungen und Interaktionen in Augmented Reality (AR) oder Virtual Reality (VR) an. Auf diesem Weg ließen sich im Gegensatz zu realen Prototypen die Gebrauchstauglichkeit und Nutzererfahrung eines Entwurfs kostensparend, mit vielen Probanden und automatisiert bewerten. Doch wie weit ist die Technologie in diesem Bereich und lassen sich hierüber wirklich Usabilityprobleme ermitteln? Im Vortrag beantworten wir diese Fragen und beleuchten, welche Interaktionsmodalitäten am besten geeignet sind und ob hierbei eine automatisierte und entfernte Evaluation möglich ist.
Informatikerinnen und Informatiker lieben Strukturen, Ordnung, Eleganz und Einfachheit. Nutzerinnen und Nutzer brauchen das auch, aber je nach Nutzergruppe anders. Demnach müssen bei der Entwicklung von Systemen die nutzergruppenspezifischen Strukturen und Ordnungen gleichzeitig berücksichtigt werden. Dadurch verlieren die Implementierungen oft an Eleganz und Einfachheit. Gibt es trotzdem Brücken, die zwischen Informatik und Usability geschlagen werden können?
Automated decision-making algorithms are increasingly prevalent in consumer-facing industries, particularly in insurance risk assessments. The traceability of these decisions is crucial for trust, acceptance, and individual autonomy. While the General Data Protection Regulation (GDPR) grants individuals the right to information about such decisions, the implementation of this right remains under-researched from a usable privacy perspective. This study employs a qualitative exploratory approach with 12 participants exercising their right to be informed about automated decision-making with German household insurers. Through interviews and observations, we investigate consumer requirements and prevailing implementation practices. Our findings unveil actual process design practices that may undermine the usability and efficacy of this data subject right. By identifying these concerns and correlating them to existing deceptive patterns, our research contributes to usable security by alerting process designers, data protection authorities, and enterprises to the significance of user-centric implementations. Furthermore, this study advances research on GDPR data subject rights, emphasizing the need for secure and usable interfaces in the context of automated decision-making systems. Our work highlights the practical challenges of safeguarding usable implementation of regulatory compliance in the realm of data protection.
Experiences With Replicable Experiments and Replication Kits for Software Engineering Research
(2019)
Replications and replicable research are currently gaining traction in the software engineering research community. Our research group made an effort in the recent years to make our own research accessible for other researchers, through the provision of replication kits that allow rerunning our experiments. Within this chapter, we present our experiences with replication kits. We first had to learn which contents are required, how to structure them, how to document them, and also how to best share them with other researchers. While this sounds very straightforward, there are many small potential mistakes, which may have a strong negative impact on the usefulness and long-term availability of replication kits. We derive best practices for the content and the sharing of replication kits based on our experiences. Moreover, we outline how platforms for replicable research may further help our community, especially with problems related to the external validity of results. Finally, we discuss the lack of integration of replication kits into most current review processes at conferences and journals. We also give one example for a review process into which replication kits were well-integrated. Altogether, this chapter demonstrates that making research replicable is a challenging task and there is a long road ahead until our community has a generally accepted and enforced standard of replicability.
Automated decision-making algorithms are increasingly prevalent in consumer-facing industries, particularly in insurance risk assessments. The traceability of these decisions is crucial for trust, acceptance, and individual autonomy. While the General Data Protection Regulation (GDPR) grants individuals the right to information about such decisions, the implementation of this right remains under-researched from a usable privacy perspective. This study employs a qualitative exploratory approach with 12 participants exercising their right to be informed about automated decision-making with German household insurers. Through interviews and observations, we investigate consumer requirements and prevailing implementation practices. Our findings unveil actual process design practices that may undermine the usability and efficacy of this data subject right. By identifying these concerns and correlating them to existing deceptive patterns, our research contributes to usable security by alerting process designers, data protection authorities, and enterprises to the significance of user-centric implementations. Furthermore, this study advances research on GDPR data subject rights, emphasizing the need for secure and usable interfaces in the context of automated decision-making systems. Our work highlights the practical challenges of safeguarding usable implementation of regulatory compliance in the realm of data protection.
Artificial Intelligence (AI) is a rising topic in the field of emotion recognition, e.g., from facial expressions. However, existing methods often require to be performed in staged set ups and are obtrusive by gathering additional data. Especially, collecting video data includes a high data protection risk. Our approach is to provide an unobtrusive emotion recognition tool based on Keystroke, Mouse and Touchscreen (KMT) data. Recently, we published a data set for emotion recognition from keystroke and mouse interaction data. In this paper, we present the challenges we faced during the creation of the data set. This covers collecting User Interface (UI) data as well as emotional ground truth data. For each of seven mentioned challenges, we provide our solutions as well as guidelines for other researchers to prevent them. The challenges include possible issues with recorded data as well as issues of automated facial coding engines. We provide a possible approach for manual facial coding and describe aspects attention should be paid to. Furthermore, we indicate issues when using different software tools to collect the data. The paper aims to help other researchers by providing insights and a guideline for the creation of the data set. We make these insights available for other researchers who want to create similar data sets or who want to expand ours. By sharing our insights, we aim to improve the reproducibility of AI training data creation and AI-based emotion recognition from user interaction data.
User experience evaluation is becoming increasingly important, and so is emotion recognition. Recognizing users’ emotions based on their interactions alone would not be intrusive to users and can be implemented in many applications. This is still an area of active research and requires data containing both the user interactions and the corresponding emotions. Currently, there is no public dataset for emotion recognition from keystroke, mouse and touchscreen dynamics. We have created such a dataset for keyboard and mouse interactions through a dedicated user study and made it publicly available for other researchers. This paper examines our study design and the process of creating the dataset. We conducted the study using a test application for travel expense reports with 50 participants. We want to be able to detect predominantly negative emotions, so we added emotional triggers to our test application. However, further research is needed to determine the relationship between user interactions and emotions.
