From Prompt to Presence: Co-Creating Personalised Emotional Sanctuaries in VR with Generative AIThe emergence of generative artificial intelligence (GenAI), combined with immersive virtual reality (VR), enables the rapid creation of personalised virtual content from simple text prompts, holding potential for emotional support. However, most current VR systems rely on pre-authored content and limit user agency in designing emotionally meaningful experiences. We introduce OasisMind, an AI-assisted VR system that empowers users to co-create 360° environments, corresponding ambient soundscapes, and context-aware digital companions through natural language prompts. In a user study (N=24), we observed how participants constructed virtual worlds for emotionally meaningful use cases and compared their creations to validated, pre-defined VR scenes recommended by previous research. Our results indicate a subjective preference for self-created environments, while no significant differences were observed in perceived satisfaction or presence between conditions. These findings suggest that user agency contributes to the emotional resonance of virtual experiences and inform the design of future personalised companion systems.2026RWRuoyu Wen et al.University of CanterburyGenerative AI (Text, Image, Music, Video)Immersion & Presence ResearchSocial & Collaborative VRIUI
Invisible Users in Digital Health: A Scoping Review of Digital Interventions to Promote Physical Activity Among CALD WomenDigital health has strong potential for promoting physical activity (PA), yet interventions often fail to sustain engagement among culturally and linguistically diverse (CALD) women. Prior reviews focus on short-term efficacy or surface-level localisation, while a design-oriented synthesis of deep cultural adaptation and long-term strategies remain limited. This scoping review systematically screened 1968 records, analysed 18 studies and identified a critical design paradox: techno-solutionist systems overlook social and cultural barriers, while social-support features often fail in low-activity social networks. To address this gap, we propose the Culturally Embedded Interaction Framework, integrating five dimensions: culturally-grounded measurement, multi-modal interaction, contextual and temporal adaptability, embedded social weaving, and theory-guided cultural adaptation. The framework advances beyond accessibility-focused approaches by mapping behavioural theory to design mechanisms that support sustained and culturally plural participation. We provide actionable design principles to help HCI researchers and practitioners move from one-size-fits-all models toward adaptive, theory-informed, and culturally sustaining design.2026YKYilin Ke et al.University of AucklandMental Health Apps & Online Support CommunitiesBehavior Change & Reflection TechnologyCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)CHI
When EmotionTech Causes Harm: The Case of Therapeutic XREmotional harm and discomfort in therapeutic extended realities (XR) remains underexamined, even as immersive tools are increasingly deployed in healthcare contexts. We frame therapeutic XR as EmotionTech and reflect on 12 cases from 9 researchers and designers through interviews and workshops. We locate four concerns for emotional harm and identify ways to address them: how to talk about emotion, when to talk about emotion, whose emotions are centred, and which emotions are valued. Building on these themes and therapeutic XR as one form of EmotionTech, we propose strategies to legitimise concerns for emotional safety in design and research practice, legitimise knowers by recognising diverse perspectives and situated experiences, and leveraging ambiguity in design and training tools that foster reflexivity rather than closure. These strategies together reposition design responsibility in EmotionTech innovation and make visible its potential to cause emotional discomforts and harms.2026TSThida Sachathep et al.The University of SydneyVR Medical Training & RehabilitationEmpathy & Emotional DesignAffective Human-Computer DialogueCHI
Towards LLM-powered Assistive Drone for Blind and Low Vision UsersDrones have gained traction as a versatile form of assistive robots for Blind and Low Vision (BLV) people. Nonetheless, novel interaction techniques are required to enable BLV people to communicate with drones naturally. In this work, we built an LLM-powered assistive drone for BLV users. We leverage an LLM to translate high-level user goals to step-by-step instructions for the drone and to extract visual information from the images. Through a formative study with BLV users (N=9), we identified envisioned use cases and desired interaction modalities. Then, we took a participatory and iterative approach to build a prototype, incorporating feedback received from 3 BLV users, as well as 5 domain experts. Finally, we conducted a user study with an additional 6 BLV participants to evaluate the iterated prototype, and received positive feedback. This work is contributing to a growing body of research on harnessing the power of LLMs to build a more inclusive world.2026YWYize Wei et al.National University of SingaporeDrone Interaction & ControlBrain-Computer Interface (BCI) & NeurofeedbackVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)CHI
AI of Oz: Enhancing Wizard of Oz Studies in HCI with AI Assistance for Human ModerationThe Wizard of Oz (WoZ) method is a common and popular approach for simulating interactive systems in Human-Computer Interaction. Running such studies is demanding for researchers because the human wizard must manage human–agent interactions in real time while keeping participants safe and the interaction natural. Many WoZ systems struggle to reproduce complex agent behaviours without minimal delays or heavy workload for the moderator. We introduce AI of Oz, a framework that uses large language models to support researchers by monitoring ongoing interactions, detecting sensitive moments, and suggesting contextually appropriate responses. In a study with 20 HCI-related researchers, the system improved participants’ ability to manage interactions and maintain control compared to a version without AI support. We outline implications for WoZ research and note current limitations and future directions.2026RWRuoyu Wen et al.University of CanterburyHuman-LLM CollaborationUser Research Methods (Interviews, Surveys, Observation)Prototyping & User TestingCHI
Cognitive Bridge: AI-Generated Boundary Objects for Cross-Functional CollaborationCross-functional teams struggle when static collaboration tools fail to keep pace with dynamic conversations. Through a formative study with seven professionals, we identified a critical gap: designers and developers speak different vocabularies, causing semantic misalignments. We present Cognitive Bridge, an AI system that monitors multimodal cues (facial expressions, speech, workspace activity) to detect emerging misunderstandings, then generates adaptive boundary objects, visual diagrams, wireframes, and flowcharts that translate between professional perspectives in real-time. Our controlled study with 16 designer-developer dyads found that Cognitive Bridge reduced communication conflicts by 47% and increased implementable solutions by 34% compared to baseline tools. However, analysis revealed a solution-exploration tradeoff: while AI accelerated alignment, it risked premature convergence that constrained creative exploration. We contribute: (1) a novel system for AI-generated boundary objects, and (2) design implications for balancing cognitive scaffolding with creative agency preservation.2026TGTamil Selvan Gunasekaran et al.The University of AucklandHuman-LLM CollaborationCrowdsourcing Task Design & Quality ControlDistributed Team CollaborationCHI
The Ocular Command Center: How Eye Responses to Luminance, Color, Tunneling, and Visual Suppression Mediate Users' Physiological States in VRThis work introduces the Ocular Command Center framework to investigate how eye responses mediate visual effects on physiology and user experience in virtual reality. In a controlled study (N=40), participants experienced variations in luminance, color temperature, peripheral occlusion, and periodic visual suppression while eye activity (pupil size, blinks, fixations, and saccades), cardiovascular responses (heart rate and heart rate variability), and subjective symptoms were measured. Luminance changes affected heart rate through pupillary reflexes. Color temperature affected heart rate variability without pupillary mediation, suggesting appraisal processes, and induced severe nausea. Peripheral occlusion and visual suppression modified oculomotor behavior without substantial cardiovascular effects. These findings demonstrate that visual manipulations could act through distinct reflexive, cognitive, and perceptual pathways, and not all extend equally to systemic physiology. This foundation supports adaptive VR design, regulating comfort, engagement, and physiological state.2026AVAndreia Valente et al.The University of AucklandImmersion & Presence ResearchSleep & Stress MonitoringEmotion Recognition & DetectionCHI
Affective and Goal-Oriented Factors of Relationship Formation in the Digital Therapeutic Alliance: A Longitudinal Study of Mental Health ChatbotsMental health chatbots are increasingly deployed as scalable interventions, yet the relational mechanisms underpinning their effectiveness remain unclear. Drawing on prior research on digital therapeutic alliance, we operationalized a preliminary multi-dimensional instrument to capture perceptions of relational and functional dynamics in mental health chatbot interactions and conducted a four-week within-subjects study with 56 participants engaging with Wysa and Youper (two widely used CBT-based mental health chatbots). Through iterative factor refinement and regression modeling, we found that user-chatbot relationship formation is primarily driven by two factors: an affective factor, centered on emotional support, and a goal-oriented factor, centered on practical assistance. Conversational control contributed alongside these interpersonal factors, while trust (privacy, non-judgmentalness) and satisfaction emerged as correlated outcomes of supportive, effective interactions rather than standalone predictors. These findings advance models of the Digital Therapeutic Alliance by clarifying its underlying structure and highlighting design priorities for balancing empathy and efficacy in conversational agents.2026ZXZian Xu et al.University of AucklandAffective Human-Computer DialogueMental Health Apps & Online Support CommunitiesCHI
Introspectus AI: Long-term AI-Driven Dialogue Training To Promote Self-ReflectionIntrospectusAI is a generative AI-based system designed to enhance self-reflection and support positive behavior change. By leveraging multimodal information from users' daily life recordings, it provides personalized and detailed feedback, aiming to deepen self-awareness and facilitate positive behavioral adjustments. This study explores the short-term and long-term impacts of interacting with IntrospectusAI, focusing on its potential to enhance reflective practices and improve the acceptance of generative AI tools. Following the user experience was defined through an initial round of workshops with four experts. The resulting system was evaluated through a long-term study involving 64 participants. The results demonstrate that AI-supported interventions significantly improved engagement in self-reflection, the need for reflection, and insight, while also increasing user acceptance of generative AI over time. These findings underscore the potential of generative AI as a practical tool for self-improvement, offering insights into its broader applicability in promoting well-being and personal growth.2025SLShengyin Li et al.Communicating With/Through AICSCW
Real-Time Full-body Interaction with AI Dance Models: Responsiveness to Contemporary Dance Interactive AI chatbots put the power of Large-Language Models (LLMs) into people's hands; it is this interactivity that fueled explosive worldwide influence. In the generative dance space, however, there are few deep-learning-based generative dance models built with interactivity in mind. The release of the AIST++ dance dataset in 2021 led to an uptick of capabilities in generative dance models. Whether these models could be adapted to support interactivity and how well this approach will work is not known. In this study, we explore the capabilities of existing generative dance models for motion-to-motion synthesis on real-time, full-body motion-captured contemporary dance data. We identify an existing model that we adapted to support interactivity: the Bailando++ model, which is trained on the AIST++ dataset and was modified to take music and a motion sequence as input parameters in an interactive loop. We worked with two professional contemporary choreographers and dancers to record and curate a diverse set of 203 motion-captured dance sequences as a set of "user inputs" captured through the Optitrack high-precision motion capture 3D tracking system. We extracted 17 quantitative movement features from the motion data using the well-established Laban Movement Analysis theory, which allowed for quantitative comparisons of inter-movement correlations, which we used for clustering input data and comparing input and output sequences. A total of 10 pieces of music were used to generate a variety of outputs using the adapted Bailando++ model. We found that, on average, the generated output motion achieved only moderate correlations to the user input, with some exceptions of movement and music pairs achieving high correlation. The high-correlation generated output sequences were deemed responsive and relevant co-creations in relation to the input sequences. We discuss implications for interactive generative dance agents, where the use of 3D joint coordinate data should be used over SMPL parameters for ease of real-time generation, and how the use of Laban Movement Analysis could be used to extract useful features and fine-tune deep-learning models.2025JZJiazhi Zhou et al.Full-Body Interaction & Embodied Input3D Modeling & AnimationIUI
Precision Email Simulator for Research on Safety-Critical Phishing BehaviourEmail is ubiquitous, and in the context of phishing, it becomes critical, as risky behaviours like clicking on phishing links or downloading malicious files can lead to severe consequences. While much research exists on phishing susceptibility, there is still a gap in understanding factors that influence user micro-behaviour when interacting with phishing emails. To address this, we offer a tool, the Precision Email Simulator, to support phishing researchers, as well as considerations in conceptualising controlled `experimental simulation' studies, which are currently underutilised in phishing research. The Precision Email Simulator simulates real-world email inboxes and tracks precision user data, such as time spent on messages and eye-tracking for key areas like URLs and sender addresses. We discuss the practical uses of our simulator, and provide recommendations and guidelines of using our email simulator.2025SZSijie Zhuo et al.University of Auckland, School of Computer ScienceOnline Harassment & Counter-ToolsIoT Device PrivacyUser Research Methods (Interviews, Surveys, Observation)CHI
Preventing Harmful Data Practices by using Participatory Input to Navigate the Machine Learning MultiverseIn light of inherent trade-offs regarding fairness, privacy, interpretability and performance, as well as normative questions, the machine learning (ML) pipeline needs to be made accessible for public input, critical reflection and engagement of diverse stakeholders. In this work, we introduce a participatory approach to gather input from the general public on the design of an ML pipeline. We show how people's input can be used to navigate and constrain the multiverse of decisions during both model development and evaluation. We highlight that central design decisions should be democratized rather than "optimized" to acknowledge their critical impact on the system's output downstream. We describe the iterative development of our approach and its exemplary implementation on a citizen science platform. Our results demonstrate how public participation can inform critical design decisions along the model-building pipeline and combat widespread lazy data practices.2025JSJan Simson et al.LMU Munich, Institut of Statistics; Munich Center for Machine Learning (MCML)AI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasParticipatory DesignCHI
Haptic Empathy: Investigating Individual Differences in Affective Haptic CommunicationsNowadays, touch remains essential for emotional conveyance and interpersonal communication as more interactions are mediated remotely. While many studies have discussed the effectiveness of using haptics to communicate emotions, incorporating affect into haptic design still faces challenges due to individual user tactile acuity and preferences. We assessed the conveying of emotions using a two-channel haptic display, emphasizing individual differences. First, 24 participants generated 187 haptic messages reflecting their immediate sentiments after watching 8 emotionally charged film clips. Afterwards, 19 participants were asked to identify emotions from haptic messages designed by themselves and others, yielding 593 samples. Our findings indicate that the ability to decode haptic messages is linked to specific emotional traits, particularly Emotional Competence (EC) and Affect Intensity Measure (AIM). Additionally, qualitative analysis revealed three strategies participants used to create touch messages: perceptive, empathetic, and metaphorical expression.2025YJYulan Ju et al.Keio University Graduate School of Media DesignVibrotactile Feedback & Skin StimulationHaptic WearablesAgent Personality & AnthropomorphismCHI
Surveillance on Exhibit: Using Problematic Technology To Teach About Problematic TechnologyAs our most advanced technologies, such as AI, become both infrastructural and opaque, experts must educate and engage the broader public. To that end, we developed an Augmented Reality (AR) museum installation about facial recognition and data collection that served both as a medium of public education and as a platform for collecting multiple different kinds of data—though, notably, not facial or other biometric data—from more than 100,000 museum visitors. We explain our design process through four animating tensions: comfort/discomfort, simplicity/complexity, neutrality/critique, and the individual/communal. Using thematic analysis of interviews and surveys, we draw insights on how people exposed to problematic technologies in a ‘safe space’ such as a museum make sense of these issues: with levity and resignation but also reverence, often specifically rooted in local cultures. We conclude with implications of the guiding principle derived from this work: “using problematic technology to teach about problematic technology.”2025EPEthan Plaut et al.University of Auckland, CommunicationPrivacy by Design & User ControlContent Moderation & Platform GovernanceMuseum & Cultural Heritage DigitizationCHI
Living Bento: Heartbeat-Driven Noodles for Enriched Dining DynamicsTo enhance focused eating and dining socialization, previous Human-Food Interaction research has indicated that external devices can support these dining objectives and immersion. However, methods that focus on the food itself and the diners themselves have remained underdeveloped. In this study, we integrated biofeedback with food, utilizing diners' heart rates as a source of the food's appearance to promote focused eating and dining socialization. By employing LED lights, we dynamically displayed diners' real-time physiological signals through the transparency of the food. Results revealed significant effects on various aspects of dining immersion, such as awareness perceptions, attractiveness, attentiveness to each bite, and emotional bonds with the food. Furthermore, to promote dining socialization, we established a “Sharing Bio-Sync Food” dining system to strengthen emotional connections between diners. Based on these findings, we developed tableware that integrates biofeedback into the culinary experience.2025WCWeijen Chen et al.Keio University Graduate School of Media DesignBiosensors & Physiological MonitoringFood Culture & Food InteractionCHI
SealMates: Improving Communication in Video Conferencing using a Collective Behavior-Driven AvatarThe limited nonverbal cues and spatially distributed nature of remote communication make it challenging for unacquainted members to be expressive during social interactions over video conferencing. Though it enables seeing others’ facial expressions, the visual feedback can instead lead to unexpected self-focus, resulting in users missing cues for others to engage in the conversation equally. To support expressive communication and equal participation among unacquainted counterparts, we propose SealMates, a behavior-driven avatar in which the avatar infers the engagement level of the group based on collective gaze and speech patterns and then moves across interlocutors' windows in the video conferencing. By conducting a controlled experiment with 15 groups of triads, we found the avatar's movement encouraged people to experience more self-disclosure and made them perceive everyone was equally engaged in the conversation than when there was no behavior-driven avatar. We discuss how a behavior-driven avatar influences distributed members' perceptions and the implications of avatar-mediated communication for future platforms.2024MAMark Armstrong et al.Session 4f: Multiplayer Gaming and CommunicationCSCW
RadarHand: a Wrist-Worn Radar for On-Skin Touch based Proprioceptive GesturesWe introduce RadarHand, a wrist-worn wearable with millimetre wave radar that detects on-skin touch-based proprioceptive hand gestures. Radars are robust, private, small, penetrate materials, and require low computation costs. We first evaluated the proprioceptive and tactile perception nature of the back of the hand and found that tapping on the thumb is the least proprioceptive error of all the finger joints, followed by the index finger, middle finger, ring finger, and pinky finger in the eyes-free and high cognitive load situation. Next, we trained deep-learning models for gesture classification. We introduce two types of gestures based on the locations of the back of the hand: generic gestures and discrete gestures. Discrete gestures are gestures that start at specific locations and end at specific locations at the back of the hand, in contrast to generic gestures, which can start anywhere and end anywhere on the back of the hand. Out of 27 gesture group possibilities, we achieved 92% accuracy for a set of seven gestures and 93% accuracy for the set of eight discrete gestures. Finally, we evaluated RadarHand’s performance in real-time under two interaction modes: Active interaction and Reactive interaction. Active interaction is where the user initiates input to achieve the desired output, and reactive interaction is where the device initiates interaction and requires the user to react. We obtained an accuracy of 87% and 74% for active generic and discrete gestures, respectively, as well as 91% and 81.7% for reactive generic and discrete gestures, respectively. We discuss the implications of RadarHand for gesture recognition and directions for future works.2024MHMr Ryo Hajika et al.Vibrotactile Feedback & Skin StimulationFoot & Wrist InteractionUIST
Modulating Heart Activity and Task Performance using Haptic Heartbeat Feedback: A Study Across Four Body PlacementsThis paper explores the impact of vibrotactile haptic feedback on heart activity when the feedback is provided at four different body locations (chest, wrist, neck, and ankle) and with two feedback rates (50 bpm and 110 bpm). A user study found that the neck placement resulted in higher heart rates and lower heart rate variability, and higher frequencies correlated with increased heart rates and decreased heart rate variability. The chest was preferred in self-reported metrics, and neck placement was perceived as less satisfying, harmonious, and immersive. This research contributes to understanding the interplay between psychological experiences and physiological responses when using haptic biofeedback resembling real body signals.2024AVAndreia Valente et al.Vibrotactile Feedback & Skin StimulationUIST
Centering Bodies in Space and Place through Virtual Reality Dance Performance: A Practice-Based Research PerspectiveOur most cutting-edge virtual reality remains focused on visual perception over embodiment. This article presents a dance performance project that stems from a foundation in somatics, creative dance, and HCI to embrace the challenge of centring bodies and embodiment within virtual reality dance performance. Our team of choreographers, dancers, and technologists recount the two-year development of the 360 video through ideation, movement tracking workshops, prototyping, process share-outs, to a final performance, to reflect on how our goal to centre bodies guided our artistic and technology choices throughout the entire process of making. Space became a key theme as we refined the choreography and design to use the full potentialities of the immersive environment. Place became a key theme as we prioritised configurations that enabled the performance to be showcased in the Pacific, Eastern Europe and Latin America. We discuss challenges and opportunities for supporting embodiment in virtual reality dance performance.2024DLDanielle Lottridge et al.Social & Collaborative VRImmersion & Presence Research360° Video & Panoramic ContentC&C
Sound Designer-Generative AI Interactions: Towards Designing Creative Support Tools for Professional Sound DesignersThe practice of sound design involves creating and manipulating environmental sounds for music, films, or games. Recently, an increasing number of studies have adopted generative AI to assist in sound design co-creation. Most of these studies focus on the needs of novices, and less on the pragmatic needs of sound design practitioners. In this paper, we aim to understand how generative AI models might support sound designers in their practice. We designed two interactive generative AI models as Creative Support Tools (CSTs) and invited nine professional sound design practitioners to apply the CSTs in their practice. We conducted semi-structured interviews and reflected on the challenges and opportunities of using generative AI in mixed-initiative interfaces for sound design. We provide insights into sound designers' expectations of generative AI and highlight opportunities to situate generative AI-based tools within the design process. Finally, we discuss design considerations for human-AI interaction researchers working with audio.2024PKPurnima Kamath et al.National University of SingaporeGenerative AI (Text, Image, Music, Video)Music Composition & Sound Design ToolsCreative Collaboration & Feedback SystemsCHI