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
JournalAIde: Empowering Older Adults in Digital Journal WritingDigital journaling offers a means for older adults to express themselves, document their lives, and engage in self-reflection, contributing to the maintenance of cognitive function and social connectivity. Although previous works have investigated the motivations and benefits of digital journaling for older adults, little technical support has been designed to offer assistance. We conducted a formative study with older adults and uncovered their encountered challenges and preferences for technical support. Informed by the findings, we designed a Large Language Model (LLM) empowered tool, JournalAIde, which provides vicarious experience, idea organization, sample text generation, and visual editing cues to enhance older adults’ confidence, writing ability, and sustained attention during digital journaling. Through a between-subjects study and a field deployment, we demonstrated the JournalAIde’s significant effectiveness compared to a baseline system in empowering older adults in digital journaling. We further investigated older adults' experiences and perceptions of LLM writing assistance.2025SZShixu Zhou et al.The Hong Kong University of Science and Technology (Guangzhou); Hong Kong University of Science and TechnologyHuman-LLM CollaborationAging-Friendly Technology DesignAI-Assisted Creative WritingCHI
"Ronaldo's a poser!": How the Use of Generative AI Shapes Debates in Online ForumsOnline debates can enhance critical thinking but may escalate into hostile attacks. As humans are increasingly reliant on Generative AI (GenAI) in writing tasks, we need to understand how people utilize GenAI in online debates. To examine the patterns of writing behavior while making arguments with GenAI, we created an online forum for soccer fans to engage in turn-based and free debates in a post format with the assistance of ChatGPT, arguing on the topic of "Messi vs Ronaldo". After 13 sessions of two-part study and semi-structured interviews with 39 participants, we conducted content and thematic analyses to integrate insights from interview transcripts, ChatGPT records, and forum posts. We found that participants prompted ChatGPT for aggressive responses, created posts with similar content and logical fallacies, and sacrificed the use of ChatGPT for better human-human communication. This work uncovers how polarized forum members work with GenAI to engage in debates online.2025YZYuhan Zeng et al.City University of Hong Kong, Department of Computer ScienceGenerative AI (Text, Image, Music, Video)Social Platform Design & User BehaviorMisinformation & Fact-CheckingCHI
" It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language ModelsPrewriting is the process of discovering and developing ideas before writing a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creative process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process.2024QWKin Chung Kwan et al.Session 3a: AI in Creative Workflows: Opportunities and ChallengesCSCW
RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data AugmentationHou 等人提出 RFBoost 框架，通过创新的物理层数据增强技术提升深度 WiFi 感知模型的泛化能力，在人体行为识别任务中准确率提升 18%。2024WHWeiying Hou et al.Context-Aware ComputingComputational Methods in HCIUbiComp
CrowdBot: An Open-Environment Robot Management System for On-Campus ServicesWang 等人设计 CrowdBot 开放环境机器人管理系统，实现校园场景下机器人的自主导航与任务调度，为校园服务机器人的高效管理提供解决方案。2024YWYufei Wang et al.Domestic RobotsSocial Robot InteractionUbiComp
Persuasion or Insulting? Unpacking Discursive Strategies of Gender Debate in Everyday Feminism in ChinaSpeaking out for women's daily needs on social media has become a crucial form of everyday feminism in China. Gender debate naturally intertwines with such feminist advocacy, where users in opposite stances discuss gender-related issues through intense discourse. The complexities of gender debate necessitate a systematic understanding of discursive strategies for achieving effective gender communication that balances civility and constructiveness. To address this problem, we adopted a mixed-methods study to navigate discursive strategies in gender debate, focusing on 38,636 posts and 187,539 comments from two representative cases in China. Through open coding, we identified a comprehensive taxonomy of linguistic strategies in gender debate, capturing five overarching themes including derogation, gender distinction, intensification, mitigation, and cognizance guidance. Further, we applied regression analysis to unveil these strategies' correlations with user participation and response, illustrating the tension between debating tactics and public engagement. We discuss design implications to facilitate feminist advocacy on social media. Content Warning: This paper contains discussions on gender debate that may include swear words and sensitive topics, such as sex, potentially causing discomfort.2024YDYue DENG et al.The Hong Kong University of Science and TechnologyGender & Race Issues in HCIEmpowerment of Marginalized GroupsCHI
mmStress: Distilling Human Stress from Daily Activities via Contact-less Millimeter-wave Sensing"Long-term exposure to stress hurts human's mental and even physical health,and stress monitoring is of increasing significance in the prevention, diagnosis, and management of mental illness and chronic disease. However, current stress monitoring methods are either burdensome or intrusive, which hinders their widespread usage in practice. In this paper, we propose mmStress, a contact-less and non-intrusive solution, which adopts a millimeter-wave radar to sense a subject's activities of daily living, from which it distills human stress. mmStress is built upon the psychologically-validated relationship between human stress and "displacement activities", i.e., subjects under stress unconsciously perform fidgeting behaviors like scratching, wandering around, tapping foot, etc. Despite the conceptual simplicity, to realize mmStress, the key challenge lies in how to identify and quantify the latent displacement activities autonomously, as they are usually transitory and submerged in normal daily activities, and also exhibit high variation across different subjects. To address these challenges, we custom-design a neural network that learns human activities from both macro and micro timescales and exploits the continuity of human activities to extract features of abnormal displacement activities accurately. Moreover, we also address the unbalance stress distribution issue by incorporating a post-hoc logit adjustment procedure during model training. We prototype, deploy and evaluate mmStress in ten volunteers' apartments for over four weeks, and the results show that mmStress achieves a promising accuracy of ~80% in classifying low, medium and high stress. In particular, mmStress manifests advantages, particularly under free human movement scenarios, which advances the state-of-the-art that focuses on stress monitoring in quasi-static scenarios." https://doi.org/10.1145/36109262023KLKun Liang et al.Human Pose & Activity RecognitionSleep & Stress MonitoringBiosensors & Physiological MonitoringUbiComp
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals"Millimeter wave (mmWave) based speech recognition provides more possibility for audio-related applications, such as conference speech transcription and eavesdropping. However, considering the practicality in real scenarios, latency and recognizable vocabulary size are two critical factors that cannot be overlooked. In this paper, we propose Radio2Text, the first mmWave-based system for streaming automatic speech recognition (ASR) with a vocabulary size exceeding 13,000 words. Radio2Text is based on a tailored streaming Transformer that is capable of effectively learning representations of speech-related features, paving the way for streaming ASR with a large vocabulary. To alleviate the deficiency of streaming networks unable to access entire future inputs, we propose the Guidance Initialization that facilitates the transfer of feature knowledge related to the global context from the non-streaming Transformer to the tailored streaming Transformer through weight inheritance. Further, we propose a cross-modal structure based on knowledge distillation (KD), named cross-modal KD, to mitigate the negative effect of low quality mmWave signals on recognition performance. In the cross-modal KD, the audio streaming Transformer provides feature and response guidance that inherit fruitful and accurate speech information to supervise the training of the tailored radio streaming Transformer. The experimental results show that our Radio2Text can achieve a character error rate of 5.7% and a word error rate of 9.4% for the recognition of a vocabulary consisting of over 13,000 words." https://doi.org/10.1145/36108732023RZRunning Zhao et al.Voice User Interface (VUI) DesignIntelligent Voice Assistants (Alexa, Siri, etc.)UbiComp
CrowdQ: Predicting the Queue State of Hospital Emergency Department Using Crowdsensing Mobility Data-Driven Models"Hospital Emergency Departments (EDs) are essential for providing emergency medical services, yet often overwhelmed due to increasing healthcare demand. Current methods for monitoring ED queue states, such as manual monitoring, video surveillance, and front-desk registration are inefficient, invasive, and delayed to provide real-time updates. To address these challenges, this paper proposes a novel framework, CrowdQ, which harnesses spatiotemporal crowdsensing data for real-time ED demand sensing, queue state modeling, and prediction. By utilizing vehicle trajectory and urban geographic environment data, CrowdQ can accurately estimate emergency visits from noisy traffic flows. Furthermore, it employs queueing theory to model the complex emergency service process with medical service data, effectively considering spatiotemporal dependencies and event context impact on ED queue states. Experiments conducted on large-scale crowdsensing urban traffic datasets and hospital information system datasets from Xiamen City demonstrate the framework's effectiveness. It achieves an F1 score of 0.93 in ED demand identification, effectively models the ED queue state of key hospitals, and reduces the error in queue state prediction by 18.5%-71.3% compared to baseline methods. CrowdQ, therefore, offers valuable alternatives for public emergency treatment information disclosure and maximized medical resource allocation." https://doi.org/10.1145/36108752023TSTieqi Shou et al.Content Moderation & Platform GovernancePublic Transit & Trip PlanningUbiComp
A Data-Driven Context-Aware Health Inference System for Children during School Closures"Many countries have implemented school closures due to the outbreak of the COVID-19 pandemic, which has inevitably affected children's physical and mental health. It is vital for parents to pay special attention to their children's health status during school closures. However, it is difficult for parents to recognize the changes in their children's health, especially without visible symptoms, such as psychosocial functioning in mental health. Moreover, healthcare resources and understanding of the health and societal impact of COVID-19 are quite limited during the pandemic. Against this background, we collected real-world datasets from 1,172 children in Hong Kong during four time periods under different pandemic and school closure conditions from September 2019 to January 2022. Based on these data, we first perform exploratory data analysis to explore the impact of school closures on six health indicators, including physical activity intensity, physical functioning, self-rated health, psychosocial functioning, resilience, and connectedness. We further study the correlation between children's contextual characteristics (i.e., demographics, socioeconomic status, electronic device usage patterns, financial satisfaction, academic performance, sleep pattern, exercise habits, and dietary patterns) and the six health indicators. Subsequently, a health inference system is designed and developed to infer children's health status based on their contextual features to derive the risk factors of the six health indicators. The evaluation and case studies on real-world datasets show that this health inference system can help parents and authorities better understand key factors correlated with children's health status during school closures. https://doi.org/10.1145/3580800"2023ZJZhihan Jiang et al.Cognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Mental Health Apps & Online Support CommunitiesUbiComp
A Personalized Visual Aid for Selections of Appearance Building Products with Long-term EffectsIt is challenging for customers to select appearance building products (e.g., skincare products, weight loss programs) that suit them personally as such products usually demonstrate efficacy only after long-term usage. Although e-retailers generally provide product descriptions or other customers' reviews, users often find it hard to relate to their own situations. In this work, we proposed a pipeline to display envisioned users' appearance after long-term use of appearance building products to deliver their efficacy on each individual visually. We selected skincare as a case and developed SkincareMirror which predicts skincare effects on users' facial images by analyzing product function labels, efficacy ratings, and skin models' images. The results of a between-subjects study (N=48) show that (1) SkincareMirror outperforms the baseline shopping site in terms of perceived usability, usefulness, user satisfaction and helps users select products faster; (2) SkincareMirror is especially effective to males and users with limited product domain knowledge.2022CSChuhan Shi et al.Hong Kong University of Science and TechnologyRecommender System UXInteractive Data VisualizationCHI
HandPainter --- 3D Sketching in VR with Hand-based Physical Proxy3D sketching in virtual reality (VR) enables users to create 3D virtual objects intuitively and immersively. However, previous studies showed that mid-air drawing may lead to inaccurate sketches. To address this issue, we propose to use one hand as a canvas proxy and the index finger of the other hand as a 3D pen. To this end, we first perform a formative study to compare two-handed interaction with tablet-pen interaction for VR sketching. Based on the findings of this study, we design HandPainter, a VR sketching system which focuses on the direct use of two hands for 3D sketching without requesting any tablet, pen, or VR controller. Our implementation is based on a pair of VR gloves, which provide hand tracking and gesture capture. We devise a set of intuitive gestures to control various functionalities required during 3D sketching, such as canvas panning and drawing positioning. We show the effectiveness of HandPainter by presenting a number of sketching results and discussing the outcomes of a user study-based comparison with mid-air drawing and tablet-based sketching tools.2021YJYing Jiang et al.The University of Hong KongHand Gesture RecognitionFull-Body Interaction & Embodied Input3D Modeling & AnimationCHI
Autocomplete Animated SculptingKeyframe-based sculpting provides unprecedented freedom to author animated organic models, which can be difficult to create with other methods such as simulation, scripting, and rigging. However, sculpting animated objects can require significant artistic skill and manual labor, even more so than sculpting static 3D shapes or drawing 2D animations, which are already quite challenging. We present a keyframe-based animated sculpting system with the capability to autocomplete user editing under a simple and intuitive brushing interface. Similar to current desktop sculpting and VR brushing tools, users can brush surface details and volume structures. Meanwhile, our system analyzes their workflows and predicts what they might do in the future, both spatially and temporally. Users can accept or ignore these suggestions and thus maintain full control. We propose the first interactive suggestive keyframe sculpting system, specifically for spatio-temporal repetitive tasks, including low-level spatial details and high-level brushing structures across multiple frames. Our key ideas include a deformation-based optimization framework to analyze recorded workflows and synthesize predictions, and a semi-causal global similarity measurement to support flexible brushing stroke sequences and complex shape changes. Our system supports a variety of shape and motion styles, including those difficult to achieve via existing animation systems, such as topological changes that cannot be accomplished via simple rig-based deformations and stylized physically-implausible motions that cannot be simulated. We evaluate our system via a pilot user study that demonstrates the effectiveness of our system.2020MPMengqi Peng et al.AI-Assisted Creative Writing3D Modeling & AnimationUIST