ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health CommunitiesOnline mental health communities (OMHCs) offer rich posts and comments for viewers, who do not directly participate in the communications, to seek social support from others’ experience. However, viewers could face challenges in finding helpful posts and comments and digesting the content to get needed support, as revealed in our formative study (N=10). In this work, we present an interactive visual tool named ComViewer to help viewers seek social support in OMHCs. With ComViewer, viewers can filter posts of different topics and find supportive comments via a zoomable circle packing visual component that adapts to searched keywords. Powered by LLM, ComViewer supports an interactive sensemaking process by enabling viewers to interactively highlight, summarize, and question any community content. A within-subjects study (N=20) demonstrates ComViewer’s strengths in providing viewers with a more simplified, more fruitful, and more engaging support-seeking experience compared to a baseline OMHC interface without ComViewer. We further discuss design implications for facilitating information-seeking and sense making in online mental health communities.2025SWShiwei Wu et al.Designing for Mental Health SupportCSCW
CoGrader: Transforming Instructors' Assessment of Project Reports through Collaborative LLM IntegrationGrading project reports are increasingly significant in today’s educational landscape, where they serve as key assessments of students' comprehensive problem-solving abilities. However, it remains challenging due to the multifaceted evaluation criteria involved, such as creativity and peer-comparative achievement. Meanwhile, instructors often struggle to maintain fairness throughout the time-consuming grading process. Recent advances in AI, particularly large language models, have demonstrated potential for automating simpler grading tasks, such as assessing quizzes or basic writing quality. However, these tools often fall short when it comes to complex metrics, like design innovation and the practical application of knowledge, that require an instructor’s educational insights into the class situation. To address this challenge, we conducted a formative study with six instructors and developed CoGrader, which introduces a novel grading workflow combining human-LLM collaborative metrics design, benchmarking, and AI-assisted feedback. CoGrader was found effective in improving grading efficiency and consistency while providing reliable peer-comparative feedback to students. We also discuss design insights and ethical considerations for the development of human-AI collaborative grading systems.2025ZCZixin Chen et al.Human-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsSTEM Education & Science CommunicationUIST
POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image GenerationState-of-the-art visual generative AI tools hold immense potential to assist users in the early ideation stages of creative tasks -- offering the ability to generate (rather than search for) novel and unprecedented (instead of existing) images of considerable quality that also adhere to boundless combinations of user specifications. However, many large-scale text-to-image systems are designed for broad applicability, yielding conventional output that may limit creative exploration. They also employ interaction methods that may be difficult for beginners. Given that creative end users often operate in diverse, context-specific ways that are often unpredictable, more variation and personalization are necessary. We introduce POET, a real-time interactive tool that (1) automatically discovers dimensions of homogeneity in text-to-image generative models, (2) expands these dimensions to diversify the output space of generated images, and (3) learns from user feedback to personalize expansions. An evaluation with 28 users spanning four creative task domains demonstrated POET's ability to generate results with higher perceived diversity and help users reach satisfaction in fewer prompts during creative tasks, thereby prompting them to deliberate and reflect more on a wider range of possible produced results during the co-creative process. Focusing on visual creativity, POET offers a first glimpse of how interaction techniques of future text-to-image generation tools may support and align with more pluralistic values and the needs of end users during the ideation stages of their work.2025EHMehtab Khan et al.Generative AI (Text, Image, Music, Video)AI-Assisted Creative WritingUIST
Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory TasksThe rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks. However, LLM-based chatbots often struggle to provide personalized support, particularly when users start with vague queries or lack sufficient contextual information. This paper introduces the Collaborative Assistant for Personalized Exploration (CARE), a system designed to enhance personalization in exploratory tasks by combining a multi-agent LLM framework with a structured user interface. CARE's interface consists of a Chat Panel, Solution Panel, and Needs Panel, enabling iterative query refinement and dynamic solution generation. The multi-agent framework collaborates to identify both explicit and implicit user needs, delivering tailored, actionable solutions. In a within-subject user study with 22 participants, CARE was consistently preferred over a baseline LLM chatbot, with users praising its ability to reduce cognitive load, inspire creativity, and provide more tailored solutions. Our findings highlight CARE's potential to transform LLM-based systems from passive information retrievers to proactive partners in personalized problem-solving and exploration. The code will be made available at https://aka.ms/chatbot-care.2025YPYingzhe Peng et al.Human-LLM CollaborationCrowdsourcing Task Design & Quality ControlIUI
Light Up Fireflies: Exploring the Design of Interpersonal Bodily Intertwinement in Social Body GamesThis paper explores the design of interpersonal bodily intertwinement in social body games. We present ``Light Up Fireflies'', a two-player VR game where players embody a single avatar, with each player responsible for controlling one half of the avatar’s body. Players must coordinate closely to navigate the virtual environment and engage with the game’s tasks, where any misalignment might cause the avatar to fall. Unlike previous research, which often focused on partial or segmented bodily interactions, our game encourages a fully integrated form of bodily coordination. Players do not merely react to each other’s movements but co-experience the avatar's body, fostering a richer and more immersive connection between them. Through a study with 16 participants, we identified three key player experiences: bodily strangeness, intertwined bodily movements, and interpersonal bodily understanding. We also provide design implications for future social body games that aim to facilitate deeper, more intertwined embodied experiences.2025YLYingtong Lu et al.Southeast University, School of Computer Science and EngineeringFull-Body Interaction & Embodied InputSocial & Collaborative VRCHI
Scaffolded Turns and Logical Conversations: Designing Humanized LLM-Powered Conversational Agents for Hospital Admission InterviewsHospital admission interviews are critical for patient care but strain nurses' capacity due to time constraints and staffing shortages. While LLM-powered conversational agents (CAs) offer automation potential, their rigid sequencing and lack of humanized communication skills risk misunderstandings and incomplete data capture. Through participatory design with clinicians and volunteers, we identified essential communication strategies and developed a novel CA that implements these strategies through: (1) dynamic topic management using graph-based conversation flows, and (2) context-aware scaffolding with few-shot prompt tuning. Technical evaluation on an admission interview dataset showed our system achieving performance comparable to or surpassing human-written ground truth, while outperforming prompt-engineered baselines. A between-subject study (N=44) demonstrated significantly improved user experience and data collection accuracy compared to existing solutions. We contribute a framework for humanizing medical CAs by translating clinician expertise into algorithmic strategies, alongside empirical insights for balancing efficiency and empathy in healthcare interactions, and considerations for generalizability.2025DLDingdong Liu et al.The Hong Kong University of Science and TechnologyConversational ChatbotsHuman-LLM CollaborationCHI
iGripper: A Semi-Active Handheld Haptic VR Controller Based on Variable Stiffness MechanismWe introduce iGripper, a handheld haptic controller designed to render stiffness feedback for gripping and clamping both rigid and elastic objects in virtual reality. iGripper directly adjusts physical stiffness by using a small linear actuator to modify the spring’s position along a lever arm, with feedback force generated by the spring's reaction to the user's input. This enables iGripper to render stiffness from zero to any specified value, determined by the spring's inherent stiffness. Additionally, a blocking mechanism is designed to provide fully rigid feedback to enlarge the rendering range. Compared to active controllers, iGripper offers a broad range of force and stiffness feedback without requiring high-power actuators. Unlike many passive controllers, which provide only braking force, iGripper, as a semi-active controller, delivers controllable elastic force feedback. We present the iGripper’s design, performance evaluation, and user studies, comparing its realism with a commercial impedance-type grip device.2025KSKe Shi et al.Southeast University, School of Instrument Science and Engineering; National University of Singapore, Department of Biomedical EngineeringForce Feedback & Pseudo-Haptic WeightShape-Changing Interfaces & Soft Robotic MaterialsCHI
LumaDreams: Designing Positive Dream Meaning-Making for Daily EmpowermentDreams contribute to cognitive and emotional health, yet tools for everyday dream engagement remain largely underexplored outside clinical settings. In this paper, we introduce LumaDreams, a mobile application designed to foster daily empowerment through positive dream transformation using generative AI. Informed by meaning-making theories, LumaDreams enables users to journal dreams through sketches and text, which are then transformed into positive images and stories for users to revisit and reflect on. We conducted a mixed-method study with 14 participants over 14 days. Our findings show that LumaDreams strengthened participants’ daily empowerment through cognitive and emotional shifts that arise from the positive meaning-making process. Qualitative insights further revealed how users’ perceptions and trust of AI-driven dream transformation were shaped through their interactions. In conclusion, we propose an inspiring approach that enables users to co-create positive meanings in dream experiences with generative AI, promoting cognitive and emotional shifts, fostering positive mindsets, and ultimately strengthening daily empowerment.2025BLBolin Lyu et al.Southeast University, School of Computer Science and EngineeringGenerative AI (Text, Image, Music, Video)Mental Health Apps & Online Support CommunitiesCHI
What Makes Digital Support Effective? How Therapeutic Skills Affect Clinical Well-BeingOnline mental health support communities have grown in recent years for providing accessible mental and emotional health support through volunteer counselors. Despite millions of people participating in chat support on these platforms, the clinical effectiveness of these communities on mental health symptoms remains unknown. Furthermore, although volunteers receive some training based on established therapeutic skills studied in face-to-face environments such as active listening and motivational interviewing, it remains understudied how the usage of these skills in this online context affects people's mental health status. In our work, we collaborate with one of the largest online peer support platforms and use both natural language processing and machine learning techniques to measure how one-on-one support chats affect depression and anxiety symptoms. We measure how the techniques and characteristics of support providers, such as using affirmation, empathy, and past experience on the platform, affect support-seekers’ mental health changes. We find that online peer support chats improve both depression and anxiety symptoms with a statistically significant but relatively small effect size. Additionally, support providers' techniques such as emphasizing the autonomy of the client lead to better mental health outcomes. However, we also found that some behaviors (e.g. persuading) are actually harmful to depression and anxiety outcomes. Our work provides key understanding for mental health care in the online setting and designing training systems for online support providers.2024AFTianmi Fang et al.Session 3b: Bridging Technology and TherapyCSCW
Integrating Equity in Public Sector Data-Driven Decision Making: Exploring the Desired Futures of Underserved StakeholdersPublic sectors aim to innovate not just for efficiency but also to enhance equity. Despite the growing adoption of data-driven decision-making systems in the public sector, efforts to integrate equity as a primary goal often fall short. This typically arises from inadequate early-stage involvement of the underserved stakeholders and prevalent misunderstandings concerning the authentic meaning of equity from these stakeholders' perspectives. Our research seeks to address this gap by actively involving undersevered stakeholders in the process of envisioning the integration of equity within public sector data-driven decisions, particularly in the context of a building department in a Northeastern mid-sized U.S. city. Applying a speed dating method with storyboards, we explore diverse equity-centric futures within the realm of local business development, a domain where small businesses, particularly women- and minority-owned businesses, historically confront inequitable distribution of public services. We explored three essential aspects of equity: monitoring equity, resource allocation prioritization, as well as information and equity. Our findings illuminate the complexities of integrating equity into data-driven decisions, offering nuanced insights about the needs of stakeholders. We found that attempts to monitor and incorporate equity goals into public sector decision-making can unexpectedly backfire, inadvertently sparking community apprehension and potentially exacerbating existing inequities. Small business owners, including those identifying as women- and minority-owned, advocated against the use of demographic-based data in equity-focused data-driven decision-making in the public sector, instead emphasizing factors like community needs, application complexity, and inherent small business uncertainties. Drawing from these insights, we propose design implications to assist designers of public sector data-driven decision-making systems better accommodate equity considerations.2024SKSeyun Kim et al.Session 2e: Data, Power, and JusticeCSCW
Studying Up Public Sector AI: How Networks of Power Relations Shape Agency Decisions Around AI Design and UseAs public sector agencies rapidly introduce new AI tools in high-stakes domains like social services, it becomes critical to understand how decisions to adopt these tools are made in practice. We borrow from the anthropological practice to ``study up'' those in positions of power, and reorient our study of public sector AI around those who have the power and responsibility to make decisions about the role that AI tools will play in their agency. Through semi-structured interviews and design activities with 16 agency decision-makers, we examine how decisions about AI design and adoption are influenced by their interactions with and assumptions about other actors within these agencies (e.g., frontline workers and agency leaders), as well as those above (legal systems and contracted companies), and below (impacted communities). By centering these networks of power relations, our findings shed light on how infrastructural, legal, and social factors create barriers and disincentives to the involvement of a broader range of stakeholders in decisions about AI design and adoption. Agency decision-makers desired more practical support for stakeholder involvement around public sector AI to help overcome the knowledge and power differentials they perceived between them and other stakeholders (e.g., frontline workers and impacted community members). Building on these findings, we discuss implications for future research and policy around actualizing participatory AI approaches in public sector contexts.2024AKAnna Kawakami et al.Session 2e: Data, Power, and JusticeCSCW
DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-ExplorationInterdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS). Based on users' topic of interest, DiscipLink initiates exploratory questions from the perspectives of possible relevant fields of study, and users can further tailor these questions. DiscipLink then supports users in searching and screening papers under selected questions by automatically expanding queries with disciplinary-specific terminologies, extracting themes from retrieved papers, and highlighting the connections between papers and questions. Our evaluation, comprising a within-subject comparative experiment and an open-ended exploratory study, reveals that DiscipLink can effectively support researchers in breaking down disciplinary boundaries and integrating scattered knowledge in diverse fields. The findings underscore the potential of LLM-powered tools in fostering information-seeking practices and bolstering interdisciplinary research.2024CZChengbo Zheng et al.Human-LLM CollaborationUser Research Methods (Interviews, Surveys, Observation)Prototyping & User TestingUIST
Can a Funny Chatbot Make a Difference? Infusing Humor into Conversational Agent for Behavioral InterventionRegular physical activity is crucial for reducing the risk of non-communicable disease (NCD). With NCDs on the rise globally, there is an urgent need for effective health interventions, with chatbots emerging as a viable and cost-effective option because of limited healthcare accessibility. Although health professionals often utilize behavior change techniques (BCTs) to boost physical activity levels and enhance client engagement and motivation by affiliative humor, the efficacy of humor in chatbot-delivered interventions is not well-understood. This study conducted a randomized controlled trial to examine the impact of the generative humorous communication style in a 10-day chatbot-delivered intervention for physical activity. It further investigated whether user engagement and motivation act as mediators between the communication style and changes in physical activity levels. 66 participants engaged with the chatbots across three groups (humorous, non-humorous, and no-intervention) and responded to daily ecological momentary assessment questionnaires assessing engagement, motivation, and physical activity levels. Multilevel time series analyses revealed that an affiliative humorous communication style positively impacted physical activity levels over time, with user engagement acting as a mediator in this relationship, whereas motivation did not. These findings clarify the role of humorous communication style in chatbot-delivered interventions for physical activity, offering valuable insights for future development of intelligent conversational agents incorporating humor.2024XSXin Sun et al.Conversational ChatbotsMental Health Apps & Online Support CommunitiesCUI
See Widely, Think Wisely: Toward Designing a Generative Multi-agent System to Burst Filter BubblesThe proliferation of AI-powered search and recommendation systems has accelerated the formation of "filter bubbles" that reinforce people's biases and narrow their perspectives. Previous research has attempted to address this issue by increasing the diversity of information exposure, which is often hindered by a lack of user motivation to engage with. In this study, we took a human-centered approach to explore how Large Language Models (LLMs) could assist users in embracing more diverse perspectives. We developed a prototype featuring LLM-powered multi-agent characters that users could interact with while reading social media content. We conducted a participatory design study with 18 participants and found that multi-agent dialogues with gamification incentives could motivate users to engage with opposing viewpoints. Additionally, progressive interactions with assessment tasks could promote thoughtful consideration. Based on these findings, we provided design implications with future work outlooks for leveraging LLMs to help users burst their filter bubbles.2024YZyu zhang et al.Southeast University, Lenovo ResearchHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityCHI
Designing Upper-Body Gesture Interaction with and for People with Spinal Muscular Atrophy in VRRecent research proposed gaze-assisted gestures to enhance interaction within virtual reality (VR), providing opportunities for people with motor impairments to experience VR. Compared to people with other motor impairments, those with Spinal Muscular Atrophy (SMA) exhibit enhanced distal limb mobility, providing them with more design space. However, it remains unknown what gaze-assisted upper-body gestures people with SMA would want and be able to perform. We conducted an elicitation study in which 12 VR-experienced people with SMA designed upper-body gestures for 26 VR commands, and collected 312 user-defined gestures. Participants predominantly favored creating gestures with their hands. The type of tasks and participants' abilities influence their choice of body parts for gesture design. Participants tended to enhance their body involvement and preferred gestures that required minimal physical effort, and were aesthetically pleasing. Our research will contribute to creating better gesture-based input methods for people with motor impairments to interact with VR.2024JTJingze Tian et al.Southeast University, The Hong Kong University of Science and Technology (Guangzhou)Full-Body Interaction & Embodied InputMotor Impairment Assistive Input TechnologiesCHI
When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design TaskStudies of Generative AI (GenAI)-assisted creative workflows have focused on individuals overcoming challenges of prompting to produce what they envisioned. When designers work in teams, how do collaboration and prompting influence each other, and how do users perceive generative AI and their collaborators during the co-prompting process? We engaged students with design or performance backgrounds, and little exposure to GenAI, to work in pairs with GenAI to create stage designs based on a creative theme. We found two patterns of collaborative prompting focused on generating story descriptions first, or visual imagery first. GenAI tools helped participants build consensus in the task, and allowed for discussion of the prompting strategies. Participants perceived GenAI as efficient tools rather than true collaborators, suggesting that human partners reduced the reliance on their use. This work highlights the importance of human-human collaboration when working with GenAI tools, suggesting systems that take advantage of shared human expertise in the prompting process.2024ZQZiyi Qiu et al.Southeast UniversityGenerative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsCHI
"Are You Really Sure?'' Understanding the Effects of Human Self-Confidence Calibration in AI-Assisted Decision MakingIn AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, "human self-confidence calibration". We begin by proposing an analytical framework to highlight the importance of calibrated human self-confidence. In our first study, we explore the relationship between human self-confidence appropriateness and reliance appropriateness. Then in our second study, We propose three calibration mechanisms and compare their effects on humans' self-confidence and user experience. Subsequently, our third study investigates the effects of self-confidence calibration on AI-assisted decision-making. Results show that calibrating human self-confidence enhances human-AI team performance and encourages more rational reliance on AI (in some aspects) compared to uncalibrated baselines. Finally, we discuss our main findings and provide implications for designing future AI-assisted decision-making interfaces.2024SMShuai Ma et al.The Hong Kong University of Science and TechnologyExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers’ Preference ElicitationPreference-based learning aims to align robot task objectives with human values. One of the most common methods to infer human preferences is by pairwise comparisons of robot task trajectories. Traditional comparison-based preference labeling systems seldom support labelers to digest and identify critical differences between complex trajectories recorded in videos. Our formative study (N = 12) suggests that individuals may overlook non-salient task features and establish biased preference criteria during their preference elicitation process because of partial observations. In addition, they may experience mental fatigue when given many pairs to compare, causing their label quality to deteriorate. To mitigate these issues, we propose FARPLS, a Feature-Augmented Robot trajectory Preference Labeling System. FARPLS highlights potential outliers in a wide variety of task features that matter to humans and extracts the corresponding video keyframes for easy review and comparison. It also dynamically adjusts the labeling order according to users’ familiarities, difficulties of the trajectory pair, and level of disagreements. At the same time, the system monitors labelers’ consistency and provides feedback on labeling progress to keep labelers engaged. . A between-subjects study (N = 42, 105 pairs of robot pick-and-place trajectories per person) shows that FARPLS can help users establish preference criteria more easily and notice more relevant details in the presented trajectories than the conventional interface. FARPLS also improves labeling consistency and engagement, mitigating challenges in preference elicitation without raising cognitive loads significantly.2024HLHanfang Lyu et al.Human-Robot Collaboration (HRC)Prototyping & User TestingIUI
Conan's Bow Tie: A Streaming Voice Conversion for Real-Time VTuber LivestreamingRecent years have witnessed a dramatic growing trend of Virtual YouTubers (VTubers) as a new business on social media, such as YouTube, Twitch, and TikTok. However, due to the health problems or retirement of voice actors, maintaining the recognizable voices of VTuber avatars becomes a critical problem that remains unsolved. One potential solution has been depicted as Conan's Bow Tie voice changer in the popular animation Case Closed (i.e., Detective Conan). To make this a reality, we introduce VTuberBowTie, a user-friendly streaming voice conversion system for real-time VTuber livestreaming. We propose an innovative streaming voice conversion approach that tackles the challenges of limited context modeling and bidirectional context dependence inherent to conventional real-time voice conversion. Rather than individually processing the voice stream in data chunks, our approach adopts a fully sequential structure that leverages contextual information preceding the input chunk, thereby expanding the perceptual range and enabling seamless concatenation. Moreover, we developed a ready-to-use interaction interface for VTuberBowTie and deployed it on various computing platforms. The experimental results show that VTuberBowTie can achieve high-quality voice conversion in a streaming manner with a latency of 179.1ms on CPU and 70.8ms on GPU while providing users a friendly interactive experience.2024QCQianniu Chen et al.Intelligent Voice Assistants (Alexa, Siri, etc.)AI-Assisted Creative WritingIUI
BLEselect: Gestural IoT Device Selection via Bluetooth Angle of Arrival Estimation from Smart Glasses"Spontaneous selection of IoT devices from the head-mounted device is key for user-centered pervasive interaction. BLEselect enables users to select an unmodified Bluetooth 5.1 compatible IoT device by nodding at, pointing at, or drawing a circle in the air around it. We designed a compact antenna array that fits on a pair of smart glasses to estimate the Angle of Arrival (AoA) of IoT and wrist-worn devices' advertising signals. We then developed a sensing pipeline that supports all three selection gestures with lightweight machine learning models, which are trained in real-time for both hand gestures. Extensive characterizations and evaluations show that our system is accurate, natural, low-power, and privacy-preserving. Despite the small effective size of the antenna array, our system achieves a higher than 90% selection accuracy within a 3 meters distance in front of the user. In a user study that mimics real-life usage cases, the overall selection accuracy is 96.7% for a diverse set of 22 participants in terms of age, technology savviness, and body structures. https://dl.acm.org/doi/10.1145/3569482"2023TZTengxiang Zhang et al.On-Skin Display & On-Skin InputContext-Aware ComputingUbiquitous ComputingUbiComp