Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character DialoguesInteractions with non-player characters (NPCs) are ubiquitous in video games but traditionally rely on scripted dialogue. The advent of large language models (LLMs) has opened up new opportunities to converse with NPCs and, in turn, contribute to player experience. However, integrating LLM-driven dialogue in games is not necessarily straightforward and needs an understanding of how this new technique is perceived by players and shapes their game experience. In this paper we contribute to this emerging line of inquiry and report on a study investigating players' perceptions on LLM-generated dialogues in a bespoke game. Towards this end, we have conducted an online survey, containing both quantitative measures and qualitative open-ended questions, with 62 participants. Our results indicate that LLM-generated dialogues have several benefits such as enhanced input flexibility or leading to more natural conversations but can create a variety of undesired side-effects that might be hard to anticipate beforehand or control for.2026MHManuel Hochreiter et al.Johannes Kepler University LinzGenerative AI (Text, Image, Music, Video)Game UX & Player BehaviorRole-Playing & Narrative GamesIUI
Framing 'Collaboration': How Human-Human Principles Translate into Human-AI RealitiesThe recent advancement of AI has shifted terminology: humans "use" computers but "collaborate with" AI. This anthropomorphic framing shapes expectations of system capabilities. Despite the large body of research adopting "human-AI collaboration" as a term, there seems to be little consensus on a definition of the concept at a glance. To address this potential gap and to provide a comprehensive overview of existing related literature, we first conducted a thematic analysis on human-human collaboration literature (n=60) to extract definitional components and associated concepts. Second, we analyzed publications on human-AI collaboration (n=299) using OpenAI’s GPT4o mini and o3 mini models, mapping the identified concepts to the AI context to examine the extent to which these concepts of collaboration are represented there. Our findings provide a shared conceptual foundation to support interdisciplinary research and suggest future research directions. Additionally, they inform the design of human-AI interfaces and interaction processes, bridging theory and practice.2026KBKarin Breckner et al.University of Applied Sciences Upper AustriaHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationParticipatory DesignCHI
Beyond Disposition: AI Knowledge Predicts Anthropomorphization of a Language Model Better Than Personality Traits in Lay and Expert PopulationsAnthropomorphizing Artificial Intelligence (AI), i.e., ascribing human-like mind or emotions to it, is widespread but varies across individuals. We tested three proposed dispositional predictors of anthropomorphism (need for cognition, need for structure, loneliness) in a general population (N = 307) and an AI expert sample (N = 130). Using a vignette design based on excerpts from a dialogue between the large language model LaMDA and one of its engineers, we found that none of the three dispositional traits predicted anthropomorphism. Instead, higher levels of AI knowledge decreased anthropomorphism across both samples. Experts reported higher AI knowledge and lower anthropomorphism than laypersons. For laypersons, anthropomorphism increased intentions to use LaMDA. For experts it did not, but was correlated with discomfort. In both samples, anthropomorphism was associated with greater moral care, i.e., not switching off LaMDA against "its will." Our findings highlight the role of knowledge and expertise in perceptions of AI.2026MMMartina Mara et al.Johannes Kepler University LinzAgent Personality & AnthropomorphismExplainable AI (XAI)AI Ethics, Fairness & AccountabilityCHI
"Hey Dashboard!": Supporting Voice, Text, and Pointing Modalities in Dashboard Onboarding using Large Language ModelsVisualization dashboards are regularly used for data exploration and analysis, but their complex interactions and interlinked views often require time-consuming onboarding sessions from dashboard authors. Preparing these onboarding materials is labor-intensive and requires manual updates when dashboards change. Recent advances in multimodal interaction powered by large language models (LLMs) provide ways to support self-guided onboarding. We present DIANA (Dashboard Interactive Assistant for Navigation and Analysis), a multimodal dashboard assistant that helps users for navigation and guided analysis through chat, audio, and mouse-based interactions. Users can choose any interaction modality or a combination of them to onboard themselves on the dashboard. Each modality highlights relevant dashboard features to support user orientation. Unlike typical LLM systems that rely solely on text-based chat, DIANA combines multiple modalities to provide explanations directly in the dashboard interface. We conducted a comparative qualitative user study to understand the use of different modalities for different types of onboarding tasks and their complexities.2026VDVaishali Dhanoa et al.Aarhus UniversityGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationInteractive Data VisualizationCHI
What Users Like and Don’t Like About Occupational Exoskeletons: Experiences and Implications From a Focus Group StudyOccupational exoskeletons are designed to support workers in strenuous tasks and to promote health, yet their implementation and use often present challenges due to the close interaction between wearer and device. This study explored user perceptions of occupational exoskeletons through qualitative focus groups conducted after participants had gained hands-on experience with 16 different devices in four-hour trials. Key findings highlight users’ feedback on system sound, design, and support, movement restriction and wearer comfort, and underscore the important role of bodily sensations–alongside factors, such as usability and appearance–in exoskeleton user experience. A central discovery was the existence of conflicts between user preferences, for instance, between light-weight designs and effective user support. Based on these insights, we highlight implications for human-centered design of exoskeletons and aim to inspire further research within the human-computer interaction community.2026SSSandra Maria Siedl et al.Johannes Kepler University LinzForce Feedback & Pseudo-Haptic WeightHaptic WearablesHuman Pose & Activity RecognitionCHI
Pathways of Desire: Enhancing Navigation and Sense of Community Through Player-Generated Desire PathsNavigating is essential in many video games. However, previous work suggests that many games still suffer from navigational problems that decrease enjoyment. In this paper, we focus on "Desire Paths", informal trails collectively created by pedestrians representing the most convenient route. While they are known to be useful wayfinding aids, it is unclear how they affect navigation and experience in games. We therefore investigated diegetically visualized player trajectory data in a 2D game through virtual footprints that were persistently visible for all subsequent players. Through a mixed-methods study involving 50 participants, we found that virtual footprints improved navigation by guiding players to points of interest and reducing disorientation for early players. However, visual clutter from excessive footprints reduced their effectiveness in later stages. They also fostered a sense of community, especially for late-stage players and prompted exploration of yet undiscovered areas. We further discuss design implications and future research directions.2025MLMichael Lankes et al.University of Applied Sciences Upper Austria, Department of Digital MediaGamification DesignMultiplayer & Social GamesCHI
The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Prospective Cardiac Rehabilitation SettingWe evaluated the viability of using Large Language Models (LLMs) to trigger and personalize content in Just-in-Time Adaptive Interventions (JITAIs) in digital health. As an interaction pattern representative of context-aware computing, JITAIs are being explored for their potential to support sustainable behavior change, adapting interventions to an individual’s current context and needs. Challenging traditional JITAI implementation models, which face severe scalability and flexibility limitations, we tested GPT-4 for suggesting JITAIs in the use case of heart-healthy activity in cardiac rehabilitation. Using three personas representing patients affected by CVD with varying severeness and five context sets per persona, we generated 450 JITAI decisions and messages. These were systematically evaluated against those created by 10 laypersons (LayPs) and 10 healthcare professionals (HCPs). GPT-4-generated JITAIs surpassed human-generated intervention suggestions, outperforming both LayPs and HCPs across all metrics (i.e., appropriateness, engagement, effectiveness, and professionalism). These results highlight the potential of LLMs to enhance JITAI implementations in personalized health interventions, demonstrating how generative AI could revolutionize context-aware computing.2025DHDavid Haag et al.Ludwig Boltzmann Institute for Digital Health and Prevention; Austrian Institute of Technology, Digital Health Information Systems, Center for Health and BioresourcesHuman-LLM CollaborationMental Health Apps & Online Support CommunitiesContext-Aware ComputingCHI
mmArrhythmia: Contactless Arrhythmia Detection via mmWave SensingZhao 等人提出 mmArrhythmia 系统，利用毫米波雷达实现无接触式心律失常检测，无需佩戴任何传感器即可监测心脏节律异常2024LZLangcheng Zhao et al.Biosensors & Physiological MonitoringUbiComp
Show me a "Male Nurse"! How Gender Bias is Reflected in the Query Formulation of Search Engine UsersBiases in algorithmic systems have led to discrimination against historically disadvantaged groups, including the reinforcement of outdated gender stereotypes. While a substantial body of research addresses biases in algorithms and underlying data, in this work, we study if and how users themselves reflect these biases in their interactions with systems, which expectedly leads to the further manifestation of biases. More specifically, we investigate the replication of stereotypical gender representations by users in formulating online search queries. Following prototype theory, we define the disproportionate mention of the gender that does not conform to the prototypical representative of a searched domain (e.g., “male nurse”) as an indication of bias. In a pilot study with 224 US participants and a main study with 400 UK participants, we find clear evidence of gender biases in formulating search queries. We also report the effects of an educative text on user behaviour and highlight the wish of users to learn about bias-mitigating strategies in their interactions with search engines.2023SKSimone Kopeinik et al.Know-CenterAI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasCHI
The Next Generation of Human-Drone Partnerships: Co-Designing an Emergency Response SystemThe use of semi-autonomous Unmanned Aerial Vehicles (UAV) to support emergency response scenarios, such as fire surveillance and search and rescue, offers the potential for huge societal benefits. However, designing an effective solution in this complex domain represents a "wicked design" problem, requiring a careful balance between trade-offs associated with drone autonomy versus human control, mission functionality versus safety, and the diverse needs of different stakeholders. This paper focuses on designing for situational awareness (SA) using a scenario-driven, participatory design process. We developed SA cards describing six common design-problems, known as SA demons, and three new demons of importance to our domain. We then used these SA cards to equip domain experts with SA knowledge so that they could more fully engage in the design process. We designed a potentially reusable solution for achieving SA in multi-stakeholder, multi-UAV, emergency response applications.2020AAAnkit Agrawal et al.University of Notre DameTeleoperation & TelepresenceParticipatory DesignCHI
Why Do You Like To Drive Automated? A Context-Dependent Analysis of Highly Automated Driving to Elaborate Requirements for Intelligent User InterfacesTechnology acceptance is a critical factor influencing the adoption of automated vehicles. Consequently, manufacturers feel obliged to design automated driving systems in a way to account for negative effects of automation on user experience. Recent publications confirm that full automation will potentially lack in the satisfaction of important user needs. To counteract, the adoption of Intelligent User Interfaces (IUIs) could play an important role. In this work, we focus on the evaluation of the impact of scenario type (represented by variations of road type and traffic volume) on the fulfillment of psychological needs. Results of a qualitative study (N=30) show that the scenario has a high impact on how users perceive the automation. Based on this, we discuss the potential of adaptive IUIs in the context of automated driving. In detail, we look at the aspects trust, acceptance, and user experience and its impact on IUIs in different driving situations.2019AFAnna-Katharina Frison et al.Automated Driving Interface & Takeover DesignAI-Assisted Decision-Making & AutomationIUI
In UX We Trust: Investigation of Aesthetics and Usability of Driver-Vehicle Interfaces and Their Impact on the Perception of Automated DrivingIn the evolution of technical systems, freedom from error and early adoption plays a major role for market success and to maintain competitiveness. In the case of automated driving, we see that faulty systems are put into operation and users trust these systems, often without any restrictions. Trust and use are often associated with users' experience of the driver-vehicle interfaces and interior design. In this work, we present the results of our investigations on factors that influence the perception of automated driving. In a simulator study, N=48 participants had to drive a SAE level 2 vehicle with either perfect or faulty driving function. As a secondary activity, participants had to solve tasks on an infotainment system with varying aesthetics and usability (2x2). Results reveal that the interaction of conditions significantly influences trust and UX of the vehicle system. Our conclusion is that all aspects of vehicle design cumulate to system and trust perception.2019AFAnna-Katharina Frison et al.Technische Hochschule Ingolstadt & Johannes Kepler UniversityAutomated Driving Interface & Takeover DesignIn-Vehicle Haptic, Audio & Multimodal FeedbackAI-Assisted Decision-Making & AutomationCHI
RESi: A Highly Flexible, Pressure-Sensitive, Imperceptible Textile Interface Based on Resistive YarnsWe present RESi (Resistive tExtile Sensor Interfaces), a novel sensing approach enabling a new kind of yarn-based, resistive pressure sensing. The core of RESi builds on a newly designed yarn, which features conductive and resistive properties. We run a technical study to characterize the behaviour of the yarn and to determine the sensing principle. We demonstrate how the yarn can be used as a pressure sensor and discuss how specific issues, such as connecting the soft textile sensor with the rigid electronics can be solved. In addition, we present a platform-independent API that allows rapid prototyping. To show its versatility, we present applications developed with different textile manufacturing techniques, including hand sewing, machine sewing, and weaving. RESi is a novel technology, enabling textile pressure sensing to augment everyday objects with interactive capabilities.2018PPPatrick Parzer et al.Haptic WearablesShape-Changing Interfaces & Soft Robotic MaterialsElectronic Textiles (E-textiles)UIST