Rationalizer: Leveraging LLM to Support User Providing the Rationales Behind the Rating of Likert Scale QuestionnairesSurveys, especially Likert scale questionnaires, are widely used in HCI to capture users’ attitudes and experiences, but numeric ratings alone provide little insight into the rationales behind those ratings. While adding open-ended text fields or post-questionnaire interviews can elicit richer explanations, they often impose extra effort, leading to survey fatigue or recall bias. To address this gap, we proposed Rationalizer, an LLM-supported questionnaire system that generates contextualized rationales to support participants articulate their explanations alongside each Likert item and rating. In a user evaluation comparing it with the traditional questionnaire that included open-ended text fields, Rationalizer increased the percentage of Likert items with rationales, sustained participants’ willingness to provide self-input rationales, and supported them in articulating longer explanations within comparable writing durations as the study progressed. Quality analyses further showed that Rationalizer yielded higher-quality rationales (i.e., justification and relevance) than the traditional questionnaire. These findings highlight the potential of LLM-supported questionnaires to enrich Likert ratings with contextualized, richer explanations.2026MSMeng Ting Shih et al.National Yang Ming Chiao Tung UniversityHuman-LLM CollaborationUser Research Methods (Interviews, Surveys, Observation)Prototyping & User TestingIUI
Fit Matters: Format–Distance Alignment Improves Conversational SearchExisting conversational search systems can synthesize information into responses, but they lack principled ways to adapt response formats to users' cognitive states. This paper investigates whether aligning format and distance, which involves matching information granularity and media to users' psychological distance, improves user experience. In a between-subjects experiment (N=464) on travel planning, we crossed two distance dimensions (temporal/spatial × near/far) with four formats varying in granularity (abstract/concrete) and media (text/image-and-text). The experiment established that format-distance alignment reduced users' risk perceptions while increasing decision confidence, perceptions of information usefulness, ease of use, enjoyment, and credibility, and adoption intentions. Concrete formats imposed higher cognitive load, but yielded productive effort when matched to near-distance tasks. Images enhanced concrete but not abstract text, suggesting multimedia benefits depend on complementarity. These findings establish format-distance alignment as a distinctive and important design dimension, enabling systems to tailor response formats to users' psychological distance.2026YYYitian Yang et al.National University of SingaporeConversational ChatbotsConversational Search & QA SystemsAI-Assisted Decision-Making & AutomationCHI
Keeping Everyone in the Game: Bringing Ability-Inclusive Family Co-Play to Unmodified Console GamesFamily co-play of video games is common and linked to family closeness and positive intergenerational interaction. Mixed-age co-play exposes controller-skill gaps that cause frustration and exclusion, yet most party games lack ability-inclusive assists. We explore ability-inclusive co-play for unmodified party and family games: We contribute (1) an open-source controller-skills benchmark; (2) the first lifespan study combining both broad age and deep skill coverage (ages 6–90; n=80; six skills), showing that gaps between children and older adults are skill-specific rather than uniform; (3) we present PartyAssist, a real-time, computer-vision-to-input system that detects on-screen state and injects micro controller-input assistance without altering game code; (4) in a feasibility study with 16 mixed-skill dyads (n=32; assisted player <10 or >50), assistance improved children’s survival time and success rate while remaining largely unnoticed and was viewed positively, while older adults detected assistance and reported mixed views. Interviews surfaced socially-considerate design nuances and implications to inform future designs to support ability-inclusive co-play across the lifespan.2026CWChieh-Yu Wen et al.National Taiwan UniversityGame AccessibilityChild-Computer Interaction DesignAging-Friendly Technology DesignCHI
“Tell Me Why You’re Asking”: Exploring How to Increase Engagement in Preference Feedback for Intelligent Notification SystemsUnderstanding how people are willing to express notification preferences is essential for designing personalized intelligent notification systems. Yet little is known about when, how, and under what conditions individuals choose to provide such input. We conducted semi-structured interviews with 33 participants, using design probes to examine the timing, methods, and concerns surrounding preference expression. Our findings make three contributions. First, we show that willingness to provide feedback depends not only on input ease and function but also on the justifiability of the moment, with requests embedded into notification-handling routines perceived as most natural. Second, we find that sustained engagement requires two forms of clarity: clarity in how to express one's preferences and clarity in how the system interprets and applies that input. Third, we reveal expectations for notification systems to act as evolving partners that distinguish temporary and situational shifts from longer-term preference changes and support mutual learning over time.2026LSLi-Ting Su et al.National Yang Ming Chiao Tung UniversityMobile Notification & Attention ManagementAI-Assisted Decision-Making & AutomationUser Research Methods (Interviews, Surveys, Observation)CHI
Designing Computational Tools for Exploring Causal Relationships in Qualitative DataExploring causal relationships for qualitative data analysis in HCI and social science research enables the understanding of user needs and theory building. However, current computational tools primarily characterize and categorize qualitative data; the few systems that analyze causal relationships either inadequately consider context, lack credibility, or produce overly complex outputs. We first conducted a formative study with 15 participants interested in using computational tools for exploring causal relationships in qualitative data to understand their needs and derive design guidelines. Based on these findings, we designed and implemented QualCausal, a system that extracts and illustrates causal relationships through interactive causal network construction and multi-view visualization. A feedback study (n=15) revealed that participants valued our system for reducing the analytical burden and providing cognitive scaffolding, yet navigated how such systems fit within their established research paradigms, practices, and habits. We discuss broader implications for designing computational tools that support qualitative data analysis.2026HMHan Meng et al.National University of SingaporeComputational Methods in HCIInteractive Data VisualizationTime-Series & Network Graph VisualizationCHI
Does Longer Phone Use Always Feel Worse? Examining How Intention and Duration Shape Evaluations of Time UsePrior work has examined how users judge their smartphone use, typically focusing on either usage duration or intention. How these two factors jointly shape such evaluations remains unclear. We conducted a two-week study with 104 participants, who reviewed their screenshots and provided labels of both usage intention and evaluation of time use. Across 73,000 sessions (6.1M screenshots), the relationship between duration and evaluation was initially linear but then bounded: positive evaluations declined and negative ones rose with longer phone use duration but both eventually stabilized, most often judged neutral. Trajectories varied by intention. Entertainment mirrored the overall trend; functional use continually lost positive evaluations, whereas information-seeking became increasingly positive during the first half hour before later declining; messaging-based connections slowly lost positive evaluations, while social media–based connections declined more quickly; finally, “no specific intention” unfolded in phases—from short positive use to regret-prone mid-length episodes to neutral long sessions.2026YTYi-Hua Tsai et al.National Yang Ming Chiao Tung UniversitySmartphone Addiction & Digital WellbeingBehavior Change & Reflection TechnologyData-Driven Personal Decision-MakingCHI
Navigating Marginalization: Toward Justice-Oriented Sociotechnical Design for Parent–Child Learning among Southeast Asian Immigrant Mothers in TaiwanThis study investigates how Southeast Asian (SEA) immigrant mothers in Taiwan participate in their children’s home-based learning. Drawing on semi-structured interviews and diary studies, we explore how these mothers navigate sociocultural constraints while fostering engagement and transmitting cultural values. Despite facing diminished agency and structural marginalization, mothers engage creatively in their children’s everyday learning interactions. Guided by a justice-oriented lens, we identify various harms and propose design implications for socio-technical systems that center recognition, reciprocity, and accountability in parent-child learning at the individual, familial, and societal levels. Our contribution lies in foregrounding the role of intersectional identity in parent-child learning and proposing justice-oriented design directions that support the flourishing of immigrant mothers within socio-technical systems.2026YCYing-Yu Chen et al.National Yang Ming Chiao Tung UniversityEmpowerment of Marginalized GroupsDeveloping Countries & HCI for Development (HCI4D)Digital Parenting & Screen Time ManagementCHI
EvaluAId: Human-AI Collaborative Evaluation of Open-Ended Student EssaysOpen-ended writing assignments are central to higher education, yet heterogeneous submissions and scale make evaluation difficult. Automated writing evaluation (AWE) promises speed but often trades away transparency and sidelines human judgment. This paper repositions AI as an on-demand collaborator that can provide specific, targeted support. In a formative study, we expose leverage points in three cognitive dimensions: evidence identification, comparative judgment, and feedback composition. Guided by these insights, we build EvaluAId, which supports interactive rubric-content mapping, adaptive benchmarking and self-calibration, and personalized, rubric-aligned feedback synthesis. Through a within-subjects study with 12 TAs, we evaluate how this approach supports grading compared with a rubric+LLM chatbot and an LLM-based AWE; EvaluAId improved alignment with expert ratings and increased graders' satisfaction. Finally, interviews with TAs, instructors, and students underscored the value of thoughtfulness supported by EvaluAId while surfacing practical considerations for integration into classroom. Together, our results argue for deliberate, evidence-first, human-in-the-loop evaluation.2026CZChao Zhang et al.Cornell UniversityHuman-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsUser Research Methods (Interviews, Surveys, Observation)CHI
Verifying or Clarifying? User Preferences for Mobile Crowdsourcing in Response to Seemingly Inconsistent Sensor DataIn the realm of smart cities, sensor technologies play a pivotal role in monitoring urban facilities and environments, providing real-time, site-specific information to residents. However, discrepancies often arise in sensor data due to variances in granularity, abstraction, and scope, which can foster uncertainty regarding the actual conditions on-site. This study explores whether, under these circumstances, individuals prefer on-site mobile crowds for verification purposes or for the provision of supplementary contextual information to aid in decision-making. Conducting an online study with 100 participants from our home country, who engaged in a think-aloud process while utilizing smart city sensor data for decision-making, our findings indicate that participants more often (54%) preferred seeking verification over supplementary contextual information (46%). Both pre-existing expectations and the sense of task urgency affected participants' choices between verification and supplementary contextual information. However, we found that the driving factor for seeking supplementary contextual information was not sensor data deviating from pre-existing expectations, but rather the absence of such pre-existing expectations. Our qualitative data also uncovered five primary motivations and four factors influencing the choice of crowdsourced information. Overall, these findings contribute to our understanding of how people leverage on-site mobile crowds to supplement sensor data in the context of smart cities.2025YCYou-Hsuan Chiang et al.Crowdsourcing & Peer ProductionCSCW
Understanding How Chatbot Phrasing Styles and Care Demonstration Influence Overweight Users’ Adherence Intention Towards Chatbots Supporting Weight Management Chatbots hold promise as a technology to aid in sustained weight management. However, determining the optimal way for chatbots to deliver advice to effectively change user behaviors remains a significant hurdle. This research investigates the effects of different chatbot communication styles and expressions of care on user satisfaction, misinterpretation, and intent to adhere to the advice in weight-related conversations. A mixed method study with 97 participants classified as overweight was conducted, dividing them into four groups based on explicit/implicit communication styles and the presence or absence of caring language. Surprisingly, the study found that most participants in the explicit communication groups viewed the chatbot as non-offensive. These participants also reported higher levels of enjoyment and a greater intention to follow the chatbot's recommendations. Utilizing caring language may diminish users' perception of the chatbot as a marketing tool, thereby increasing their willingness to interact. The article discusses the implications for the design of healthcare chatbots.2025WCWen-Hsuan Cheng et al.AI-Assisted HealthcareCSCW
Synthia: Visually Interpreting and Synthesizing Feedback for Writing RevisionWhile recent advances in HCI and generative AI have improved authors' access to feedback on their work, the abundance of critiques can overwhelm writers and obscure actionable insights. We introduce Synthia, a system that visually scaffolds feedback-based writing revision with LLM-powered synthesis. Synthia helps authors strategize their revisions by breaking down large feedback collections into interactive visual bubbles that can be clustered, colored, and resized to reveal patterns and highlight valuable suggestions. Bidirectional highlighting links each feedback unit to its original context and relevant parts of the text. Writers can selectively combine feedback units to generate alternative drafts, enabling rapid, parallel exploration of revision possibilities. These interactions support feedback curation, interpretation, and experimentation throughout the revision process. A within-subjects study (N=12) showed that Synthia helped participants identify more helpful feedback, explore more diverse revisions, and revise with greater intentionality and transparency than a GPT-4-based writing interface.2025CZChao Zhang et al.Generative AI (Text, Image, Music, Video)Human-LLM CollaborationInteractive Data VisualizationUIST
JettingPointer: Enabling Skin-to-Pointer Midair Touch Interaction on Minimal Wearables Using Integrated Airflow Haptic CuesWe introduce JettingPointer, a skin-to-pointer interaction technique that enables accurate near-surface 2D touch input on minimal wearable devices, such as smart glasses. The core component is an airflow jet, embedded in the glasses frame, that functions as a haptic pointer by providing localized feedback to the finger skin during touch interactions performed above the frame. Users activate functions by aligning their finger phalanx with the airflow stream, guided by proprioception and a distinct point sensation. We optimized the airflow using fluid dynamics principles and characterized the required flow rate for stable tactile perception. In Study 1, we validated its perceptual clarity, confirming that a perceptible point sensation could be reliably achieved within 20 mm of the nozzle. In Study 2, participants performed eyes-free touch tasks with nearly three times greater accuracy when supported by haptic feedback (7.49<< vs. 21.85<< error). These findings demonstrate the potential of JettingPointer as a practical method for enabling proprioception-guided, near-surface interaction on compact wearables, with implications for expanding dense input in space-constrained form factors.2025YFYuan-Ling Feng et al.Mid-Air Haptics (Ultrasonic)Haptic WearablesMobileHCI
Surrogate Avatar: Enhancing Situated Co-Presence and User Mobility in Symmetric Telepresence ConversationsWe present Surrogate Avatar, an adaptive telepresence method that enhances user mobility and situated co-presence in symmetric avatar-mediated communication. The system enables a remote user’s avatar to autonomously position itself in socially and environmentally appropriate locations within the local user’s space—based on spatial affordances, interactional norms, and environmental constraints—supporting fluid interaction without requiring a shared environmental context. Through a formative study, we derived key adaptation objectives and implemented them using a distributed optimization framework based on the AUIT system. The framework distributes adaptation tasks across server and client to balance responsiveness and computational efficiency. A user study involving both stationary and nomadic scenarios demonstrated consistently high usability and presence, with some limitations observed under walking conditions. An additional exploratory field study in a semi-structured public setting demonstrated the system’s viability beyond controlled lab conditions. These findings motivate future designs of mobile telepresence systems that dynamically adapt to spatial and conversational context while mitigating misunderstandings that can arise from asymmetric environmental awareness and supporting privacy-sensitive interaction.2025SLSheng-Cian Lee et al.Teleoperation & TelepresenceMobileHCI
From Overwhelmed to Overview: Understanding Smartphone Users' Preferences and Expectations in Relieving Notification Overload via Text SummarizationTo help users manage the overwhelming influx of smartphone notifications, this study explores how large language models (LLMs) can be leveraged to generate notification summaries. We developed an Android application that integrates ChatGPT to summarize notifications and conducted an in-the-wild deployment to examine how users guided the model. To further understand user expectations for LLM-generated summaries, we interviewed 20 participants following a week-long engagement with the app. Our findings reveal five main strategies that users employed in their prompts for generating summaries. Additionally, interviewees expected summaries to prioritize three types of notifications, preferred three levels of information disclosure influenced by content anticipation and perceived criticality, and used three different approaches to synthesizing notifications based on their interrelationships. Finally, interviewees envisioned notification summarization functioning like a virtual assistant, desiring capabilities beyond simple information condensation, including support for task and information management, revisiting archived content, and tracking activities for reflection.2025UCUei-Dar Chen et al.Human-LLM CollaborationNotification & Interruption ManagementMobileHCI
Bridging Coaching Knowledge and AI Feedback to Enhance Motor Learning in Basketball Shooting Mechanics Through a Knowledge-Based SOP FrameworkWe present a methodology for designing an AI feedback system aimed at assisting basketball beginners in refining their shooting techniques during independent practice sessions. Mastering shooting mechanics requires consistent, precise repetition, which traditionally depends on coaching feedback and the breakdown of movements into steps during the early stages. However, due to limited coaching resources, this guidance is often unavailable, leading to ineffective and even detrimental motor learning. To bridge this gap, we propose a Standard Operating Procedure (SOP) framework grounded in expert human knowledge, or knowledge-based SOP, which allows our AI-driven system to verify and guide players' movements in real-time. Through a formative study involving interviews with 13 coaches and players, we identified key challenges faced by beginners, such as uncertainty in movement correctness and lack of guidance during unsupervised practice. Our AI system addresses these issues by providing immediate, actionable feedback using SOP tailored to individual players. In a study with 28 participants, we confirmed that our system improves shooting form, increases confidence in adjustments, and enhances self-awareness during practice. This work highlights the potential of integrating coaching expertise with AI to empower athletes with more effective tools for self-directed practice.2025JWJian-Jia Weng et al.National Tsing Hua University, Institute of Service ScienceMultiplayer & Social GamesFitness Tracking & Physical Activity MonitoringCHI
What Social Media Use Do People Regret? An Analysis of 34K Smartphone Screenshots with Multimodal LLMSmartphone users often regret aspects of their phone use, especially social media use. However, pinpointing specific ways in which the design of an interface contributes to regrettable use can be challenging due to the complexity of social media app features and user intentions. We conducted a one-week study with 17 Android users, using a novel method where we passively collected screenshots every five seconds, which we analyzed via a multimodal large language model to understand participants’ usage activity at a fine-grained level. Triangulating this data with data from experience sampling, surveys, and interviews, we found that regret varies based on user intention, with non-intentional and social media use being especially regrettable. Regret also varies by social media activity; participants were most likely to regret viewing algorithmically recommended content and comments. Additionally, participants frequently deviated to browsing social media when their intention was direct communication, which slightly increased their regret. Our findings provide guidance to designers and policy-makers seeking to improve users’ experience and autonomy.2025LGLongjie Guo et al.University of Washington, The Information SchoolExplainable AI (XAI)Social Platform Design & User BehaviorMisinformation & Fact-CheckingCHI
SeeThroughBody: Mitigating Occlusion through Body Transparency to Enhance Touch Interaction between the Foot and Interactive FloorOcclusion, often caused by the user's body or fingers, can significantly reduce the efficiency and usability of touch interfaces. As foot-based interactions in HMDs become more prevalent, self-occlusion becomes a more pronounced issue due to the involvement of the body and legs. This work presents SeeThroughBody, a body-rendering approach designed to mitigate occlusion and enhance touch interactions between the foot and interactive floor in virtual environments. Our user study unveiled twofold results. First, changing VisualizationStyles and BodyPartsVisibility can improve objective performance (e.g., time, movement) by reducing occlusion. Second, these modifications also affect the subjective user experience (e.g., embodiment, usability). Different VisualizationStyles and BodyPartsVisibility have varying impacts, presenting trade-offs between performance and experience. Based on these insights, we recommend Transparent-Foot and Outline-Foot for interactions focused on efficiency, and Transparent-All and Transparent-Thigh for enhancing overall user experience. Finally, we demonstrate the application of these recommendations in a map browsing scenario using foot touch.2025MSMeng Ting Shih et al.National Yang Ming Chiao Tung University, Institute of Computer Science and EngineeringFull-Body Interaction & Embodied InputFoot & Wrist InteractionCHI
Friction: Deciphering Writing Feedback into Writing Revisions through LLM-Assisted ReflectionThis paper introduces Friction, a novel interface designed to scaffold novice writers in reflective feedback-driven revisions. Effective revision requires mindful reflection upon feedback, but the scale and variability of feedback can make it challenging for novice writers to decipher it into actionable, meaningful changes. Friction leverages large language models to break down large feedback collections into manageable units, visualizes their distribution across sentences and issues through a co-located heatmap, and guides users through structured reflection and revision with adaptive hints and real-time evaluation. Our user study (N=16) showed that Friction helped users allocate more time to reflective planning, attend to more critical issues, develop more actionable and satisfactory revision plans, iterate more frequently, and ultimately produce higher-quality revisions, compared to the baseline system. These findings highlight the potential of human-AI collaboration to foster a balanced approach between maximum efficiency and deliberate reflection, supporting the development of creative mastery.2025CZChao Zhang et al.Cornell UniversityHuman-LLM CollaborationAI-Assisted Creative WritingCHI
Understanding How Psychological Distance Influences User Preferences in Conversational versus Web SearchConversational search offers an easier and faster alternative to conventional web search, while having downsides like a lack of source verification. Research has examined performance disparities between these two systems in various settings. However, little work has investigated how changes in the nature of a search task affect user preferences. We investigate how psychological distance - the perceived closeness of one to an event - affects user preferences between conversational and web search. We hypothesise that tasks with different psychological distances elicit different information needs, which in turn affect user preferences between systems. Our study finds that, under fixed condition ordering, greater psychological distances lead users to prefer conversational search, which they perceive as more credible, useful, enjoyable, and easy to use. We reveal qualitative reasons for these differences and provide design implications for search system designers.2025YYYitian Yang et al.National University of Singapore, Computer ScienceConversational ChatbotsExplainable AI (XAI)CHI
Exploring Effects of Chatbot's Interpretation and Self-disclosure on Mental Illness StigmaChatbots are increasingly being used in mental healthcare – e.g., for assessing mental-health conditions and providing digital counseling – and have been found to have considerable potential for facilitating people’s behavioral changes. Nevertheless, little research has examined how specific chatbot designs may help reduce public stigmatization of mental illness. To help fill that gap, this study explores how stigmatizing attitudes toward mental illness may be affected by conversations with chatbots that have 1) varying ways of expressing their interpretations of participants’ statements and 2) different styles of self-disclosure. More specifically, we implemented and tested four chatbot designs that varied in terms of whether they interpreted participants’ comments as stigmatizing or non-stigmatizing, and whether they provided stigmatizing, non-stigmatizing, or no self-disclosure of chatbot's own views. Over the two-week period of the experiment, all four chatbots’ conversations with our participants centered on seven mental-illness vignettes, all featuring the same character. We found that the chatbot featuring non-stigmatizing interpretations and non-stigmatizing self-disclosure performed best at reducing the participants’ stigmatizing attitudes, while the one that provided stigmatizing interpretations and stigmatizing self-disclosures had the least beneficial effect. We also discovered side effects of chatbot’s self-disclosure: notably, that chatbots were perceived to have inflexible and strong opinions, which undermined their credibility. As such, this paper contributes to knowledge about how chatbot designs shape users’ perceptions of the chatbots themselves, and how chatbots’ interpretation and self-disclosure may be leveraged to help reduce mental-illness stigma.2024YCYichao Cui et al.Session 3b: Bridging Technology and TherapyCSCW