From Pets to Robots: MojiKit as a Data-Informed Toolkit for Affective HRI DesignDesigning affective behaviors for animal-inspired social robots often relies on intuition and personal experience, leading to fragmented outcomes. To provide more systematic guidance, we first coded and analyzed human–pet interaction videos, validated insights through literature and interviews, and created structured reference cards that map the design space of pet-inspired affective interactions. Building on this, we developed MojiKit, a toolkit combining reference cards, a zoomorphic robot prototype (MomoBot), and a behavior control studio. We evaluated MojiKit in co-creation workshops with 18 participants, finding that MojiKit helped them design 35 affective interaction patterns beyond their own pet experiences, while the code-free studio lowered the technical barrier and enhanced creative agency. Our contributions include the data-informed structured resource for pet-inspired affective HRI design, an integrated toolkit that bridges reference materials with hands-on prototyping, and empirical evidence showing how MojiKit empowers users to systematically create richer, more diverse affective robot behaviors.2026LHLiwen He et al.The Hong Kong University of Science and Technology (Guangzhou)Social Robot InteractionEmotion Recognition & DetectionEmpathy & Emotional DesignCHI
N-ary Gaussian Model Modeling Pointing Uncertainty Across Task Scenarios Using an Automated Multi-Gaussian Modeling PipelineThis paper presents an N-ary Gaussian Model for predicting endpoint distributions in pointing tasks across task scenarios. Built on the foundational principles of the Ternary Gaussian model series, our model framework allows researchers to define parameter constraints and automatically refine model combinations, eliminating the need for predefined equations based on data analysis. We utilize the Bayesian Information Criterion (BIC) for model selection, ensuring simplicity while maintaining predictive accuracy. We conducted a comparative analysis against published baselines across 7 diverse datasets, covering 1D, 2D, and 3D tasks, different input modalities, different display devices, and time-constrained scenarios, demonstrating the robustness and generalization of the N-ary Gaussian Model. The N-ary Gaussion model offers an automated solution for modeling pointing uncertainty, and also incorporates cross output device, input modality, and temporal constraint factors into spatial pointing uncertainty modeling for the first time.2026HZHao Zhang et al.Chinese Academy of SciencesTouchscreen Usability & Performance Modeling (Fitts' Law)Touch Target Selection & PointingComputational Methods in HCICHI
Echoes of Norms: Investigating Counterspeech Bots’ Influence on Bystanders in Online CommunitiesCounterspeech offers a non-repressive approach to moderate hate speech in online communities. Research has examined how counterspeech chatbots restrain hate speakers and support targets, but their impact on bystanders remains unclear. Therefore, we developed a counterspeech strategy framework and built \textit{Civilbot} for a mixed-method within-subjects study. Bystanders generally viewed Civilbot as credible and normative, though its shallow reasoning limited persuasiveness. Its behavioural effects were subtle: when performing well, it could guide participation or act as a stand-in; when performing poorly, it could discourage bystanders or motivate them to step in. Strategy proved critical: cognitive strategies that appeal to reason, especially when paired with a positive tone, were relatively effective, while mismatch of contexts and strategies could weaken impact. Based on these findings, we offer design insights for mobilizing bystanders and shaping online discourse, highlighting when to intervene and how to do so through reasoning-driven and context-aware strategies.2026MWMengyao Wang et al.Fudan UniversityContent Moderation & Platform GovernanceCyberbullying & Online HarassmentAffective Human-Computer DialogueCHI
Continuous Measurement Methods for Transient Physiological Discomfort in VR LocomotionMotion sickness, in addition to its persistent long-term effects, also exhibits short-term effects characterized as transient physiological discomfort, which changes rapidly with variations in locomotion. However, such discomforts are challenging to assess using current subjective scales and objective physiological measurements. To tackle this issue, this paper suggests continuous measurement methods designed specifically for evaluating transient physiological discomfort during VR locomotion. Through a user-elicitation study, three preferred measurement methods—'squeezing ball', 'sliding thumb', and 'rubbing thigh'—were identified. These techniques were then evaluated for reliability, validity, attention, presence, and workload, with 'sliding thumb' identified as the most effective option. The paper expands traditional measurement methods to capture users' physiological experiences in VR interactions, offering practical choices for researchers in this field along with an in-depth discussion of design considerations, detailed implementation guidelines, and potential ways to optimize the VR experiences utilizing the measurement data.2026TLTianren Luo et al.Institute of SoftwareMotion Sickness & Passenger ExperienceImmersion & Presence ResearchCHI
From Preference to Performance: Patient-Centered Design of Multimodal Cueing in Parkinson’s Disease Gait TrainingParkinson’s disease (PD) commonly leads to gait disorders that necessitate long-term rehabilitation dependent on specialists and clinic-based interventions. To reduce dependence on clinicians and investigate how wearable technology can provide continuous guidance for rehabilitation training. We distilled key design principles from patient–clinician interviews and co-designed a gait training system. The system employs inertial measurement units (IMUs) to capture kinematic data, then delivers multimodal cueing (visual, auditory, and somatosensory) aligned with walking features. Two user studies (N = 16 PD patients) evaluated the effectiveness of multimodal cueing, examining strategies for information delivery and gait correction. Results indicated that visual and auditory cueing were more effective for process-oriented adjustments, whereas somatosensory stimulation better supported periodic cueing. Moreover, a dissociation between performance outcomes and user preferences was observed. These findings highlight the potential of wearable technology to provide continuous, daily training guidance for PD patients.2026XLXinjin Li et al.Chinese Academy of SciencesHaptic WearablesVibrotactile Feedback & Skin StimulationBiosensors & Physiological MonitoringCHI
Selecting Tangible Media for Immersive Exploration of Volumetric Scientific DataImmersive scientific data exploration faces challenges in precise and efficient interaction. Tangible media offer a potential solution; but designers lack clear guidance on choosing the appropriate physical dimensionality (1D, 2D, or 3D) for different tasks. To address this problem, we present a design space structuring the relationship between the representative techniques on scientific data visualization and exploration, tangible interactions, and media dimensionality. We further developed a prototype to empirically explore these relationships according to our design space. In a controlled user study, we compared 1D, 2D, and 3D tangible media across seven core techniques. The results demonstrated that the 3D media (e.g., a box) were preferred when tasks required manipulating the entire volumetric data and acted as a proxy. Regarding the tasks requiring 2D operations or interior localization, the 2D media (e.g., a card) offered superior performance. For single-parameter techniques like histogram-based filtering, the 1D media (e.g., a pen) were overwhelmingly preferred for their simplicity and perceived ease of use.2026ZWZhouhao Wu et al.Renmin University of ChinaTangible User Interface DesignPhysical-Digital Hybrid InteractionMedical & Scientific Data VisualizationCHI
ElectroGrasp: Electrotactile Aids for Visually Impaired Individuals in Anticipatory Planning and Control of GraspGrasping objects typically relies on visual input to pre-shape the hand and plan movement trajectories, a process often disrupted in visually impaired (VI) individuals. ElectroGrasp is a wearable electro-tactile system that delivers anticipatory proprioceptive and tactile information through three complementary modalities: Grasping Orientation, Size, and Shape. This system dynamically conveys spatial features-thereby enhancing anticipatory grasp planning and control through tactile perception. Three experiments were conducted to evaluate ElectroGrasp. The first examined tactile pattern discriminability, size perception thresholds, and the reliability of orientation encoding. The second assessed learning time with ElectroGrasp and its effectiveness in supporting spatial representation, demonstrating accurate spatial perception of objects from electrotactile input. The third compared grasp aperture under audio versus electrotactile cues, revealing that ElectroGrasp reduced hand overshoot and regrasp corrections. Overall, the results demonstrate that ElectroGrasp provides efficient tactile information, enables improved anticipatory grasp planning comparable to visual cues, and offers a novel assistive solution for VI users.2026HZHechuan Zhang et al.Institute of Software, Chinese Academy of SciencesVibrotactile Feedback & Skin StimulationHaptic WearablesVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)CHI
How They Type: Eye and Finger Movement Strategies in Typing of Individuals with Cerebral PalsyTyping is essential for communication, yet the input behavior of individuals with cerebral palsy (CP) remains underexplored. We investigated 31 CP typists and 31 non-disabled controls using keystroke logging, eye tracking, and motion capture. Our study found that CP typists were slower and less rhythmically stable, but by prioritizing accuracy, their overall keyboard efficiency was comparable to controls. They adopted compensatory visual strategies such as shorter and more frequent fixations, greater reliance on the keyboard, and more gaze shifts, and displayed diverse finger usage strategies from single-finger to multi-finger input. We found that using more fingers did not necessarily result in faster typing. Subtype analysis showed spastic CP typists followed a "slow but steady" rhythm with consistent inter-key intervals, whereas athetoid CP typists exhibited a "fast but unstable" rhythm with greater variability, highlighting distinct mechanisms of typing in CP and providing insights for personalized assistive technologies.2026TSTingting Song et al.Institute of Psychology, Chinese Academy of SciencesMotor Impairment Assistive Input TechnologiesEye/Head-Controlled TypingHealth Self-TrackingCHI
"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online DiscussionsAsynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclear and warrant investigation. To address these gaps, we conducted a design workshop to explore AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase. A within-subject study (N=60) involving five consecutive asynchronous discussions showed that the agent consistently promoted deeper knowledge progression, with different styles exerting distinct effects on both content and experience. These findings provide actionable guidance for designing adaptive AI agents that sustain more constructive online discussions.2026YZYuanhao Zhang et al.Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationUser Research Methods (Interviews, Surveys, Observation)CHI
More Than a Dictionary: How AI Scaffolds the Journey from Digital Outsider to InsiderOnline communities often develop shared symbolic vocabularies that strengthen insider bonds but implicitly marginalize newcomers. On Chinese platforms, this dynamic is exemplified by “absurd language,” a style distinguished by irony, exaggeration, and local memes. While this form of expression fosters in-group intimacy, it creates significant cultural barriers for “Sino-digital non-natives.” This study investigates how AI can mediate cultural integration beyond mere translation. We developed an AI mediator integrating Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG) to scaffold this journey. A mixed-methods evaluation (N=14) demonstrates significant improvements in comprehension accuracy over a baseline LLM. Crucially, our qualitative analysis reveals a novel five-stage model of cultural integration. This model charts the user's journey from peripheral observation to confident participation, detailing the AI's evolving role from “expert guide” to “creative collaborator.” Our findings illuminate the dynamics of agency and trust, offering a framework for designing AI as a catalyst for community integration.2026YXYao Xiao et al.Academy of Information & Art designHuman-LLM CollaborationMultilingual & Cross-Cultural Voice InteractionActivism & Political ParticipationCHI
ShakeSense: An Electrotactile System to Simulate Shaking a Container with Fluid ContentsShaking a cup of wine or other fluids in virtual environments is engaging but has been limited by challenges in delivering real-time haptic feedback for liquid collisions. ShakeSense is a haptic rendering system that integrates electrotactile stimulation with physics-based simulation to deliver immersive feedback for liquid dynamics in handheld containers. It employs a high-density electrode array to deliver dynamic tactile sensations, conveying friction and pressure changes on the user's fingerpad. A dedicated end-to-end pipeline computes fingerpad forces from liquid-container-finger interactions, ensuring feedback aligns with natural fluid movement. Two studies evaluated ShakeSense’s performance and user perception. Study 1 showed that electrotactile patterns were distinguishable across directions, and synchronizing container movement with stimulation enhanced perceived force changes. Study 2 demonstrated that ShakeSense effectively simulated liquid motion, capturing multidimensional, coordinated interactions, and outperformed conventional Center-of-Mass approaches. Overall, ShakeSense provides clear, fine-grained tactile feedback for fluid interactions.2026ZHZhenxuan He et al.Institute of software, Chinese Academy of SciencesMid-Air Haptics (Ultrasonic)Shape-Changing Interfaces & Soft Robotic MaterialsImmersion & Presence ResearchCHI
Designing for Long-Term Emotion Regulation: A Breathing Biofeedback Game for Women in Compulsory Isolation Drug Rehabilitation CentersIn the rehabilitation process of women with substance use disorders, difficulties in emotion regulation represent a major risk factor for relapse, while shame, low self-esteem, and cognitive impairments further undermine their ability to learn and sustain emotion regulation skills. To address the lack of research on long-term skill transfer among marginalized populations in closed environments, we designed and evaluated a seven-day phased breathing biofeedback game based on low-cost audio input. The game was intended to support skill acquisition and transfer, strengthen self-efficacy and self-acceptance, and sustain attention and long-term engagement. In a six-week controlled study involving 60 participants, the results demonstrated that the game not only maintained high levels of engagement but also effectively improved breathing skills, facilitated their transfer into daily life, and alleviated negative emotions. Finally, we discussed and reflected on five design implications that emerged from these findings.2026QCQi Chen et al.Wuhan Textile UniversityAffective Feedback & Emotion Regulation InterfacesHealth Self-TrackingBehavior Change & Reflection TechnologyCHI
"I Know You Are Discriminatory!": Automated Substantiating for Individual Fairness Auditing of AI SystemsArtificial intelligence (AI) systems are playing an increasingly crucial role in people's lives, and their frequent unfair behaviors raise concerns about fairness. To unveil the unfairness in AI systems, researchers conduct fairness auditing on these systems. However, existing fairness auditing works often focus on group fairness while ignoring discriminatory phenomena among individuals. To unearth discriminatory phenomena against individuals within AI systems, this paper proposes an individual fairness auditing framework, termed "substantiating", which can identify discrimination instances within AI systems by constructing individual samples. To construct these samples for substantiating, auditors often have to rely on subjective prior knowledge, lacking guidelines on how to construct unfair samples. To address this issue, this paper introduces two categories of automated sample generation methods that can rapidly find unfair samples within a limited number of queries to the system and demonstrate their effectiveness through experiments. This paper evaluates the proposed auditing framework among three categories of stakeholders in AI fairness: auditors, AI model developers, and non-technical personnel. The research findings point out their demand for individual fairness audits of AI systems and highlight how the framework supports a reliable and convenient individual fairness audit.2025YLYuanhao Liu et al.Facilitating Equity and Fairness in TechCSCW
SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM InteractionHuman interaction with large language models (LLMs) is typically confined to text or image interfaces. Sketches offer a powerful medium for articulating creative ideas and user intentions, yet their potential remains underexplored. We propose SketchGPT, a novel interaction paradigm that integrates sketch and speech input directly over the system interface, facilitating open-ended, context-aware communication with LLMs. By leveraging the complementary strengths of multimodal inputs, expressions are enriched with semantic scope while maintaining efficiency. Interpreting user intentions across diverse contexts and modalities remains a key challenge. To address this, we developed a prototype based on a multi-agent framework that infers user intentions within context and generates executable context-sensitive and toolkit-aware feedback. Using Chain-of-Thought techniques for temporal and semantic alignment, the system understands multimodal intentions and performs operations following human-in-the-loop confirmation to ensure reliability. User studies demonstrate that SketchGPT significantly outperforms unimodal manipulation approaches, offering more intuitive and effective means to interact with LLMs.2025ZHZeyuan Huang et al.Voice User Interface (VUI) DesignHuman-LLM CollaborationUIST
Assessing Dynamic Flow Experience from EEG Signals: A Processing-based ApproachAs an interaction experience goal, the flow experience is characterized by its subjectivity and dynamism. Exploring objective methods to assess dynamic flow states is significant in enhancing user experience design, evaluation, and optimization. This study aims to model the dynamics of the flow experience and quantify its intensity using electroencephalography signals (EEG) from the perspective of the process. To achieve this, an interactive task is designed to induce dynamic changes in flow, and EEG signals from participants were recorded simultaneously, to form a flow assessment dataset. Subsequently, a frequency-aware convolutional Transformer model (FA-ConFormer) was proposed to extract dynamic features from EEG, with particular optimization for capturing complex dynamic features in the frequency domain. Experimental results demonstrate that FA-ConFormer outperforms existing methods in flow state and intensity recognition, the visualization of the flow process dynamically depicting the onset, development, peak, and decline of flow with varying intensities, which help to deepen the understanding of flow experience.2025SLShilong Liu et al.Brain-Computer Interface (BCI) & NeurofeedbackVisualization Perception & CognitionUIST
Unknown Word Detection for English as a Second Language (ESL) Learners using Gaze and Pre-trained Language ModelsEnglish as a Second Language (ESL) learners often encounter unknown words that hinder their text comprehension. Automatically detecting these words as users read can enable computing systems to provide just-in-time definitions, synonyms, or contextual explanations, thereby helping users learn vocabulary in a natural and seamless manner. This paper presents EyeLingo, a transformer-based machine learning method that predicts the probability of unknown words based on text content and eye gaze trajectory in real time with high accuracy. A 20-participant user study revealed that our method can achieve an accuracy of 97.6%, and an F1-score of 71.1%. We implemented a real-time reading assistance prototype to show the effectiveness of EyeLingo. The user study shows improvement in willingness to use and usefulness compared to baseline methods.2025JDJiexin Ding et al.Tsinghua University, Key Laboratory of Pervasive Computing, Ministry of Education, Department of Computer Science and Technology, Global Innovation Exchange (GIX) Institute; University of Washington, Paul G. Allen School of Computer Science & EngineeringHuman Pose & Activity RecognitionHuman-LLM CollaborationCHI
PANDA: Parkinson's Assistance and Notification Driving AidParkinson's Disease (PD) significantly impacts driving abilities, often leading to early driving cessation or accidents due to reduced motor control and increasing reaction times. To diminish the impact of these symptoms, we developed PANDA (Parkinson's Assistance and Notification Driving Aid), a multi-modality real-time alert system designed to monitor driving patterns continuously and provide immediate alerts for irregular driving behaviors, enhancing driver safety of individuals with PD. The system was developed through a participatory design process with 9 people with PD and 13 non-PD individuals using a driving simulator, which allowed us to identify critical design characteristics and collect detailed data on driving behavior. A user study involving individuals with PD evaluated the effectiveness of PANDA, exploring optimal strategies for delivering alerts and ensuring they are timely and helpful. Our findings demonstrate that PANDA has the potential to enhance the driving safety of individuals with PD, offering a valuable tool for maintaining independence and confidence behind the wheel.2025TWTianyang Wen et al.Institude of Software, Chinese Academy of SciencesIn-Vehicle Haptic, Audio & Multimodal FeedbackMotor Impairment Assistive Input TechnologiesPrototyping & User TestingCHI
Exploring the Remapping Impact of Spatial Head-hand Relations in Immersive TelesurgeryThe action remapping between the user and the avatar creates significant perceptual and behavioral challenges. Recently, in addition to virtual environments, remapping has also given rise to new applications—immersive teleoperated robots. This paper selects immersive telesurgery, a representative scenario, as an opportunity for research, exploring the generalized effects of remapping. In such a scenario, the operator can observe through the robot's camera and use their hands to control the robotic arms, as if they were the robot. However, common remapping of spatial head-hand relations—due to camera adjustments and robotic arm switching—creates significant visual-proprioceptive conflicts and physical limitations. To explore this, we simulated a telesurgery system with 6 head-camera and 12 hand-robotic-arm remapping conditions, assessing non-surgeon participants across four surgical tasks: navigation, location, cutting, and bimanual coordination. The study examines spatial perception bias, interaction deviation, workload, and task completion time. Our findings reveal how different remapping targets, attributes, intensities, and situations affect performance, contributing to the understanding of perception mechanisms and offering insights for optimizing operations or systems.2025TLTianren Luo et al.Institute of Software, Chinese Academy of Sciences; College of Computer Science and Technology, University of Chinese Academy of SciencesTeleoperated DrivingHuman-Robot Collaboration (HRC)CHI
VAction: A Lightweight and Integrated VR Training System for Authentic Film-Shooting ExperienceThe film industry exerts significant economic and cultural influence, and its rapid development is contingent upon the expertise of industry professionals, underscoring the critical importance of film-shooting education. However, this process typically necessitates multiple practice in complex professional venues using expensive equipment, presenting a significant obstacle for ordinary learners who struggle to access such training environments. Despite VR technology has already shown its potential in education, existing research has not addressed the crucial learning component of replicating the shooting process. Moreover, the limited functionality of traditional controllers hinder the fulfillment of the educational requirements. Therefore, we developed VAction VR system, combining high-fidelity virtual environments with a custom-designed controller to simulate the real-world camera operation experience. The system’s lightweight design ensures cost-effective and efficient deployment. Experiment results demonstrated that VAction significantly outperforms traditional methods in both practice effectiveness and user experience, indicating its potential and usefulness in film-shooting education.2025SWShaocong Wang et al.Tsinghua University, Department of Computer Science and TechnologyMixed Reality WorkspacesHome Energy ManagementCHI
Emotionally Challenging Games Can Satisfy Older Adults' Psychological Needs: From Empirical Study to Design GuidelinesOlder adults often struggle to meet their psychological needs due to retirement and living alone. Recent studies suggest that games featuring emotional challenge (EC) can help fulfill basic psychological needs such as autonomy, competence, and relatedness by facilitating emotional exploration. However, it remains unclear whether older adults can benefit from EC games, whether they find this genre enjoyable, and how these games should be designed to better meet their needs. This work explores older adults’ experiences and perceptions of playing EC games through two studies. The first study involved playing Detroit: Become Human, revealing that older adults derived multifaceted psychological experiences from playing the game. The second study involved a custom-designed game scenario tailored to older adults, demonstrating that meaningful choices significantly influenced autonomy need satisfaction. Based on these findings, we offer five design guidelines for developing EC games that satisfy psychological needs of older adults.2025MZMin Zhou et al.Institute of Software, ChineseAging-Friendly Technology DesignSerious & Functional GamesCHI