Educational videos are widely used, but accessibility guidelines beyond captions for d/Deaf and Hard-of-Hearing (DHH) learners remain limited. Mayer’s multimedia learning theory assumes visual-auditory dual-channel processing, yet DHH learners with limited access to the auditory channel have distinct visual abilities and cognitive demands. This paper introduces motion-driven design ideas to support cognitive processing and improve video-based learning for DHH learners. Through a three-phase study, we identified four key challenges—such as misaligned content and visual overload—and proposed four design ideas that extend multimedia learning theory. We then evaluated these ideas with 16 DHH learners and 6 experts in Deaf education. The results show that motion-driven approaches reduce misalignment, ease visual attention switching, and improve the integration of visual and textual information across video types. For example, guiding visual attention switching minimizes confusion in complex visual contexts, such as programming demonstrations, while using relevant visuals enriches talking-head videos with graphics to clarify abstract ideas in captions. More research is needed to develop these promising ideas into well-defined principles.

Immersive technologies are increasingly applied in therapeutic and well-being practices, yet most AR systems focus on dyadic client–avatar interactions and overlook richer therapeutic structures that involve therapists. We introduce AReframedChair, an AR system that reimagines the traditional Empty Chair technique by enabling self-dialogue with a personalized avatar representing one’s past or future self. In a between-subjects study with 60 adults, we compared the traditional Empty Chair method with two AR-reframed modes: Dyadic (client–avatar) and Triadic (client–avatar– therapist). Participants’ survey responses showed that the Dyadic mode elicited greater positive affect and self-compassion in the past-self scenarios, whereas the Triadic mode produced stronger gains in motivation and reflections in future-self scenarios. Thematic analysis further revealed distinct roles: the Avatar facilitated emotional entry, reassurance, and cognitive reframing, while the Therapists intervened at critical moments to down-regulate intensity, redirect attention, and enhance reflection. These findings open up new design pathways for mental health technologies.

Early-stage interdisciplinary research ideation is often challenged by limited expert access, uncertainty about what to ask, and the cognitive burden of synthesizing unfamiliar domain perspectives. This paper presents Perspectra, a forum-style multi-agent system that structures and visualizes deliberation among LLM-simulated domain experts to support exploration and refinement of emerging research ideas, while encouraging critical thinking and reflections. The interface design combines 1) a threaded canvas for parallel topic exploration with visualization of agent discourse dynamics informed by argumentation theory to aid sensemaking; and 2) feature that enables users to invite multiple self-chosen agents into an ongoing discussion. We conducted a user study with 18 participants, comparing Perspectra against a vanilla chat baseline given a task for the user to develop a short research proposal. Our findings show that Perspectra’s design elicits significantly more higher-order critical thinking behaviors during interactions with agents when compared to a traditional chat interface. We also observed more interdisciplinary user replies via forum-styled design, and more frequent and structured proposal revisions (rather than unstructured note-taking). Based on our findings, we further contribute interaction design implications of using multi-agent deliberation for complex ideation and knowledge search, combining flexibility with structured exploration to support user sensemaking and critical thinking.

The integration of generative AI with Extended Reality (XR) technologies has unlocked unprecedented capabilities, empowering users with enhanced cognitive, sensory, and environmental control – effectively enabling "superpowers" in immersive digital spaces. This paper explores both the benefits and potential risks. We make two contributions: (i) a synthesized taxonomy of LLM-enabled XR superpowers and their associated risks, and (ii) a set of design guidelines and a forward research agenda derived from that synthesis. We conduct a multi-phase analysis of 135 recent advancements and studies in the field to examine the superpowers granted by these technologies, alongside their associated risks. We categorize the superpowers into internal (cognitive and sensory enhancements) and external (environmental and social manipulations), illustrating how they amplify human abilities in domains such as healthcare, education, and professional training. We then analyze the risks specific to each superpower, revealing critical vulnerabilities in user autonomy, data security, and ethical transparency. This research aims to guide stakeholders in harnessing the potential of XR while mitigating the socio-technical risks of this emerging landscape.

Emergency evacuation in VR must balance realism with clear guidance. However, most prior studies strengthen either sensory or social factors in isolation, leaving equal-geometry causal estimates of load versus crowd still lacking. We present SAFE-VR, a controlled testbed that orthogonally varies Environmental Load (low vs. high) and Crowd Dynamics (orderly vs. chaotic) while keeping layout, signage, and spawn constant. In a preregistered 2 x 2 between-subjects experiment (N=80), we analyzed time-to-exit, frame-coded behavior, presence, and workload to distangle sensory from social effects. Both factors impaired egress, with the High×Chaotic condition performing worst overall. For time-to-exit, effects were additive (no reliable Load×Crowd interaction); in contrast, Temporal demand showed a crossed interaction. High load increased effort, frustration, and object contacts; while chaotic flow increased route deviations, human contacts, and slowed exits. These patterns align with reliability-weighted cueing: as guidance becomes harder to perceive, participants may shift toward crowd-following, especially when flow is unstable. SAFE-VR thus delineates how load and crowd structure jointly shape route fidelity, collisions, and evacuation time, and highlights conditions where subjective time pressure diverges from objective delay.

○ where users can indicate their topics of interest for exploration.Persona Nodes 2 ○ represent AI-simulated expert perspectives that can suggest related literature retrieved from online publication database (Literature Nodes 3 ○), and subsequently provide feedback and critiques (Critique Nodes 4 ○) to users' initial research idea.Based on the critiques and identified literature, the system can further help revise users' initial idea into a revised RQ (RQ node 5 ○).Users can perform this process iteratively and combine inputs from multiple expert personas until they discover satisfactory RQs of their interest.

Large Language Models (LLMs) are increasingly used by teenagers and young adults in everyday life, ranging from emotional support and creative expression to educational assistance. However, their unique vulnerabilities and risk profiles remain under-examined in current safety benchmarks and moderation systems, leaving this population disproportionately exposed to harm. In this work, we present Youth AI Risk (YAIR), the first benchmark dataset designed to evaluate and improve the safety of youth–LLM interactions. YAIR consists of 12,449 annotated conversation snippets spanning 78 fine-grained risk types, grounded in a taxonomy of youth-specific harms such as grooming, boundary violation, identity confusion, and emotional overreliance. We systematically evaluate widely adopted moderation models on YAIR and find that existing approaches substantially underperform in detecting youth-centered risks, often missing contextually subtle yet developmentally harmful interactions. To address these gaps, we introduce YouthSafe, a real-time risk detection model optimized for youth–GenAI contexts. YouthSafe significantly outperforms prior systems across multiple metrics on risk detection and classification, offering a concrete step toward safer and more developmentally appropriate AI interactions for young users.

Unlike the free exploration of childhood, the demands of daily life reduce our motivation to explore our surroundings, leading to missed opportunities for informal learning. Traditional tools for knowledge acquisition are reactive, relying on user initiative and limiting their ability to uncover hidden interests. Through formative studies, we introduce AiGet, a proactive AI assistant integrated with AR smart glasses, designed to seamlessly embed informal learning into low-demand daily activities (e.g., casual walking and shopping). AiGet analyzes real-time user gaze patterns, environmental context, and user profiles, leveraging large language models to deliver personalized, context-aware knowledge with low disruption to primary tasks. In-lab evaluations and real-world testing, including continued use over multiple days, demonstrate AiGet's effectiveness in uncovering overlooked yet surprising interests, enhancing primary task enjoyment, reviving curiosity, and deepening connections with the environment. We further propose design guidelines for AI-assisted informal learning, focused on transforming everyday moments into enriching learning experiences. © 2025 Copyright held by the owner/author(s).

Given the widespread presence of screens during meals, the notion that digital engagement is inherently incompatible with mindfulness. We demonstrate how the strategic design of digital content can enhance two core aspects of mindful eating: slow eating and food awareness. Our research unfolded in three sequential studies: (1). Zoom Eating Study: Contrary to the assumption that video-watching leads to distraction and overeating, this study revealed that subtle video speed manipulations—can promote slower eating (by 15.31%) and controlled food intake (by 9.65%) while maintaining meal satiation and satisfaction. (2). Co-design workshop: Informed the development of ViFeed, a video playback system strategically incorporating subtle speed adjustments and glanceable visual cues. (3). Field Study: A week-long deployment of ViFeed in daily eating demonstrated its efficacy in fostering food awareness, food appreciation, and sustained engagement. By bridging the gap between ideal mindfulness practices and screen-based behaviors, this work offers insights for designing digital-wellbeing interventions that align with, rather than against, existing habits. © 2025 Copyright held by the owner/author(s).

Despite the prevalence of autism spectrum disorder (ASD) and other developmental disabilities (DD) worldwide, children with ASD and DD face tremendous difficulties receiving support due to physical, financial, and psychological barriers to onsite health and education clinics. As a result, researchers and practitioners have designed software solutions aimed at providing accessible support to meet users’ needs. However, we have limited knowledge of whether these solutions indeed work in real-world settings. To address this gap, we conducted a case study on a cognitive training program called Dubupang, designed by Dubu Inc. From in-depth interviews with multiple stakeholders and field observations of children with ASD and DD, we identify Dubu Inc.’s internal development processes, the critical design issues that emerged through a series of field trials (e.g., instructional design and feedback), and the key implications (e.g., importance of caregivers’ strategic human interventions) for design that better supports both children with ASD and DD and their caregivers.

Peer Reviewed

This study investigates innovative interaction designs for communication and collaborative learning between learners of mixed hearing and signing abilities, leveraging advancements in mixed reality technologies like Apple Vision Pro and generative AI for animated avatars. Adopting a participatory design approach, we engaged 15 d/Deaf and hard of hearing (DHH) students to brainstorm ideas for an AI avatar with interpreting ability (sign language to English and English to sign language) that would facilitate their face-to-face communication with hearing peers. Participants envisioned the AI avatars to address some issues with human interpreters, such as lack of availability, and provide affordable options to expensive personalized interpreting services. Our findings indicate a range of preferences for integrating the AI avatars with actual human figures of both DHH and hearing communication partners. The participants highlighted the importance of having control over customizing the AI avatar, such as AI-generated signs, voices, facial expressions, and their synchronization for enhanced emotional display in communication. Based on our findings, we propose a suite of design recommendations that balance respecting sign language norms with adherence to hearing social norms. Our study offers insights into improving the authenticity of generative AI in scenarios involving specific and sometimes unfamiliar social norms.

Accessibility efforts for d/Deaf and hard of hearing (DHH) learners in video-based learning have mainly focused on captions and interpreters, with limited attention to learners' emotional awareness--an important yet challenging skill for effective learning. Current emotion technologies are designed to support learners' emotional awareness and social needs; however, little is known about whether and how DHH learners could benefit from these technologies. Our study explores how DHH learners perceive and use emotion data from two collection approaches, self-reported and automatic emotion recognition (AER), in video-based learning. By comparing the use of these technologies between DHH (N=20) and hearing learners (N=20), we identified key differences in their usage and perceptions: 1) DHH learners enhanced their emotional awareness by rewatching the video to self-report their emotions and called for alternative methods for self-reporting emotion, such as using sign language or expressive emoji designs; and 2) while the AER technology could be useful for detecting emotional patterns in learning experiences, DHH learners expressed more concerns about the accuracy and intrusiveness of the AER data. Our findings provide novel design implications for improving the inclusiveness of emotion technologies to support DHH learners, such as leveraging DHH peer learners' emotions to elicit reflections.

Emotional support is a crucial aspect of communication between community members and police dispatchers during incident reporting. However, there is a lack of understanding about how emotional support is delivered through text-based systems, especially in various non-emergency contexts. In this study, we analyzed two years of chat logs comprising 57,114 messages across 8,239 incidents from 130 higher education institutions. Our empirical findings revealed significant variations in emotional support provided by dispatchers, influenced by the type of incident, service time, and a noticeable decline in support over time across multiple organizations. To improve the consistency and quality of emotional support, we developed and implemented a fine-tuned Large Language Model (LLM), named dispatcherLLM, designed to suggest replies through simulating human dispatchers' languages with appropriate emotional support. We evaluated dispatcherLLM by comparing its generated responses to those of human dispatchers and other off-the-shelf models using real chat messages. Additionally, we conducted a human evaluation to assess the perceived effectiveness of the support provided by dispatcherLLM. This study not only contributes new empirical understandings of emotional support in text-based dispatch systems but also demonstrates the significant potential of generative AI in improving service delivery.

Optical See-through Head-Mounted Displays (OHMDs) offer new opportunities for completing complex information processing tasks on the go. We introduce GlassMail, a Large Language Models (LLMs)-based wearable assistant on OHMDs for mobile email creation. Our formative study identified two challenges of the LLM-based wearable email assistant: (i) achieving efficient and accurate understanding of user intentions, and (ii) ensuring effective information presentation for email processes. Through two empirical studies, we developed a "Single Turn with Optional Clarification " approach for accurate user intention recognition and a "Fade Context with Optional Audio " mode for effective email processing. An observation study then evaluated GlassMail ’s feasibility in composing formal and semi-formal emails, supporting the usefulness and effectiveness of GlassMail in simple scenarios and yielding insights into potential future improvements for complex scenarios. We further discuss the design implications for the future development of wearable AI-enabled assistants.

Previous research underscored the potential of danmaku–a text-based commenting feature on videos–in engaging hearing audiences. Yet, for many Deaf and hard-of-hearing (DHH) individuals, American Sign Language (ASL) takes precedence over English. To improve inclusivity, we introduce “Signmaku,” a new commenting mechanism that uses ASL, serving as a sign language counterpart to danmaku. Through a need-finding study (N=12) and a within-subject experiment (N=20), we evaluated three design styles: real human faces, cartoon-like figures, and robotic representations. The results showed that cartoon-like signmaku not only entertained but also encouraged participants to create and share ASL comments, with fewer privacy concerns compared to the other designs. Conversely, the robotic representations faced challenges in accurately depicting hand movements and facial expressions, resulting in higher cognitive demands on users. Signmaku featuring real human faces elicited the lowest cognitive load and was the most comprehensible among all three types. Our findings offered novel design implications for leveraging generative AI to create signmaku comments, enriching co-learning experiences for DHH individuals.

Developing novel research questions (RQs) often requires extensive literature reviews, especially in interdisciplinary fields. To support RQ development through human-AI co-creation, we leveraged Large Language Models (LLMs) to build an LLM-based agent system named CoQuest. We conducted an experiment with 20 HCI researchers to examine the impact of two interaction designs: breadth-first and depth-first RQ generation. The findings revealed that participants perceived the breadth-first approach as more creative and trustworthy upon task completion. Conversely, during the task, participants considered the depth-first generated RQs as more creative. Additionally, we discovered that AI processing delays allowed users to reflect on multiple RQs simultaneously, leading to a higher quantity of generated RQs and an enhanced sense of control. Our work makes both theoretical and practical contributions by proposing and evaluating a mental model for human-AI co-creation of RQs. We also address potential ethical issues, such as biases and over-reliance on AI, advocating for using the system to improve human research creativity rather than automating scientific inquiry. The system’s source is available at: https://github.com/yiren-liu/coquest.

The rise of multitasking in contemporary lifestyles has positioned audio-first content as an essential medium for information consumption. We present AudioXtend, an approach to augment audiobook experiences during daily tasks by integrating glanceable, AI-generated visuals through optical see-through head-mounted displays (OHMDs). Our initial study showed that these visual augmentations not only preserved users’ primary task efficiency but also dramatically enhanced immediate auditory content recall by 33.3% and 7-day recall by 32.7%, alongside a marked improvement in narrative engagement. Through participatory design workshops involving digital arts designers, we crafted a set of design principles for visual augmentations that are attuned to the requirements of multitaskers. Finally, a 3-day take-home field study further revealed new insights for everyday use, underscoring the potential of assisted reality (aR) to enhance heads-up listening and incidental learning experiences.

The think-aloud protocol is an effective method frequently used by designers and researchers to understand how users interact with computing systems. However, there is limited research on the use of this method with deaf and hard of hearing (DHH) populations, especially in virtual settings. In this paper, we investigate the behaviors of DHH participants in virtual think-aloud sessions to better understand the challenges of conducting this type of research with this population. We conducted twelve virtual think-aloud sessions with DHH participants using Zoom, and we gathered feedback from surveys, interviews, and observations. Our results identified DHH behaviors leading to a lack of clarity in think-aloud data, such as asynchrony between signing and navigating the interfaces, as well as the use of visual descriptive signs instead of explicit terminology to ambiguously refer to interface components. Based on our findings, we provide methodological and design implications to help researchers effectively carry out virtual think-aloud studies with DHH participants (e.g., when and how to prompt for clarification).

Empathy for children is critical for designing AI technologies that may affect children. This paper presents the work in progress of a study on the feasibility of a new method to provide objective understanding of people’s empathy for children based on functional near infrared spectroscopy (fNIRS). Adult participants (n=13) were presented with benign or concerning scenarios involving children interacting with AI technologies. Their brain activation patterns were recorded and analyzed. Preliminary data analysis revealed distinctive patterns in the mPFC region, which justifies future work to fully realize the potential of this method.

Causal reasoning is crucial for people to understand data, make decisions, or take action. However, individuals often have blind spots and overlook alternative hypotheses, and using only data is insufficient for causal reasoning. We designed and implemented CrowdIDEA, a novel tool consisting of a three-panel integration incorporating the crowd’s beliefs (Crowd Panel with two designs), data analytics (Data Panel), and user’s causal diagram (Diagram Panel) to stimulate causal reasoning. Through an experiment with 54 participants, we showed the significant effects of the Crowd Panel designs on the outcomes of causal reasoning, such as an increased number of causal beliefs generated. Participants also devised new strategies for bootstrapping, strengthening, deepening, and explaining their causal beliefs, as well as taking advantage of the unique characteristics of both qualitative and quantitative data sources to reduce potential biases in reasoning. Our work makes theoretical and design implications for exploratory causal reasoning.

Today’s cybersecurity and AI technologies are often fraught with ethical challenges. One promising direction is to teach cybersecurity and AI ethics to today’s youth. However, we know little about how these subjects are taught before college. Drawing from interviews of US high school teachers (n=16) and students (n=11), we find that cybersecurity and AI ethics are often taught in non-technical classes such as social studies and language arts. We also identify relevant topics, of which epistemic norms, privacy, and digital citizenship appeared most often. While teachers leverage traditional and novel teaching strategies including discussions (treating current events as case studies), gamified activities, and content creation, many challenges remain. For example, teachers hesitate to discuss current events out of concern for appearing partisan and angering parents; cyber hygiene instruction appears very ineffective at educating youth and promoting safer online behavior; and generational differences make it difficult for teachers to connect with students. Based on the study results, we offer practical suggestions for educators, school administrators, and cybersecurity practitioners to improve youth education on cybersecurity and AI ethics.

Ethnic minorities face challenges in sustaining their culture in regions dominated by ethnic majorities. With the growing popularity of video blogging (vlogging) in China, many ethnic minority vloggers are using vlogs to present and promote their ethnic culture online. In this study, we interviewed 16 vloggers onDouyin to understand why and how vlogs can be used to sustain ethnic culture. We found that both ethnic cultural experts and non-experts were involved in ethnic vlog making and sharing activities onDouyin, and cultural experts took more initiative in preserving and promoting ethnic culture while non-experts were more motivated by getting more traffic and income. Vloggers' imagined audiences included both intra-ethnic and mainstream viewers, impacting their vlog-making strategies, the utilized platform features, and the created vlog content. For example, vloggers taught ethnic language and built an identity for intra-ethnic viewers. Both ethnic minority vloggers and viewers protected their culture from misinterpretation by mainstream viewers. Our findings suggest the potential of using video blogging to address the challenges of cultural sustainability, providing design implications for future ICTs to support the cultural sustainability of ethnic minorities.

Learners' awareness of their own affective states (emotions) can improve their meta-cognition, which is a critical skill of being aware of and controlling one's cognitive, motivational, and affect, and adjusting their learning strategies and behaviors accordingly. To investigate the effect of peers' affects on learners' meta-cognition, we proposed two types of cues that aggregated peers' affects that were recognized via facial expression recognition:Locative cues (displaying the spikes of peers' emotions along a video timeline) andTemporal cues (showing the positivities of peers' emotions at different segments of a video). We conducted a between-subject experiment with 42 college students through the use of think-aloud protocols, interviews, and surveys. Our results showed that the two types of cues improved participants' meta-cognition differently. For example, interacting with theTemporal cues triggered the participants to compare their own affective responses with their peers and reflect more on why and how they had different emotions with the same video content. While the participants perceived the benefits of using AI-generated peers' cues to improve their awareness of their own learning affects, they also sought more explanations from their peers to understand the AI-generated results. Our findings not only provide novel design implications for promoting learners' meta-cognition with privacy-preserved social cues of peers' learning affects, but also suggest an expanded design framework for Explainable AI (XAI).

Recently, an increasing number of safety organizations in the U.S. have incorporated text-based risk reporting systems to respond to safety incident reports from their community members. To gain a better understanding of the interaction between community members and dispatchers using text-based risk reporting systems, this study conducts a system log analysis ofLiveSafe, a community safety reporting system, to provide empirical evidence of the conversational patterns between users and dispatchers using both quantitative and qualitative methods. We created an ontology to capture information (e.g., location, attacker, target, weapon, start-time, and end-time, etc.) that dispatchers often collected from users regarding their incident tips. Applying the proposed ontology, we found that dispatchers often asked users for different information across varied event types (e.g.,Attacker forAbuse andAttack events,Target forHarassment events). Additionally, using emotion detection and regression analysis, we found an inconsistency in dispatchers' emotional support and responsiveness to users' messages between different organizations and between incident categories. The results also showed that users had a higher response rate and responded quicker when dispatchers provided emotional support. These novel findings brought significant insights to both practitioners and system designers, e.g., AI-based solutions to augment human agents' skills for improved service quality.

Understanding emerging safety risks in nuanced social VR spaces and how existing safety features are used is crucial for the future development of safe and inclusive 3D social worlds. Prior research on safety risks in social VR is mainly based on interview or survey data about social VR users' experiences and opinions, which lacks "in-situ observations" of how individuals react to these risks. Using two empirical studies, this paper seeks to understand safety risks and safety design in social VR. In Study 1, we investigated 212 YouTube videos and their transcripts that document social VR users' immediate experiences of safety risks as victims, attackers, or bystanders. We also analyzed spectators' reactions to these risks shown in comments to the videos. In Study 2, we summarized 13 safety features across various social VR platforms and mapped how each existing safety feature in social VR can mitigate the risks identified in Study 1. Based on the uniqueness of social VR interaction dynamics and users' multi-modal simulated reactions, we call for further re-thinking and re-approaching safety designs for future social VR environments and propose potential design implications for future safety protection mechanisms in social VR.

Emotion is important for the conversational user interface. In prior research, conversational agents (CAs) employ natural language process techniques to create affective interaction based on text. However, the use of acoustic features of speech for voice-based CAs is under exploration. This work presents an acoustically emotion-aware CA that enables speech emotion recognition and stylizes responses with empathetic feedback and interjections. We conducted an experiment with 75 participants to evaluate their perceived emotional intelligence (PEI) after interacting with the CA. Our results show that the acoustical emotion-awareness increased the participants’ PEI of the CA, and the empathetic responses from the CA helped alleviate some participants’ negative emotions. Our work provides implications for designing future CAs with better PEI.

Prior research suggests that affective states of self-regulated learning can be used to improve learners’ cognitive processes and their learning outcomes. However, little research explored the effect of using facial movements to detect learners’ affective states on self-regulated learning. In this work, we designed, implemented, and evaluated Mirror: a self-regulated learning tool that applies facial expression recognition to support learners’ reflections in video-based learning. We conducted two studies to identify user needs (with 12 participants) and to evaluate the tool (with 16 participants). The results show that, after watching a video, participants benefited from using Mirror through different reflection processes, e.g., gaining a deeper understanding of their learning experiences through self-observation and attributing causes for their learning affects through self-judgment. Meanwhile, we also identified several ethical concerns, e.g., users’ agency of handling the uncertainty of AI, reactivity towards outcome-based AI, over-reliance on “positive” AI results, and fairness of AI informed decision-making.

Early conversational agents (CAs) focused on dyadic human-AI interaction between humans and the CAs, followed by the increasing popularity of polyadic human-AI interaction, in which CAs are designed to mediate human-human interactions. CAs for polyadic interactions are unique because they encompass hybrid social interactions, i.e., human-CA, human-to-human, and human-to-group behaviors. However, research on polyadic CAs is scattered across different fields, making it challenging to identify, compare, and accumulate existing knowledge. To promote the future design of CA systems, we conducted a literature review of ACM publications and identified a set of works that conducted UX (user experience) research. We qualitatively synthesized the effects of polyadic CAs into four aspects of human-human interactions, i.e., communication, engagement, connection, and relationship maintenance. Through a mixed-method analysis of the selected polyadic and dyadic CA studies, we developed a suite of evaluation measurements on the effects. Our findings show that designing with social boundaries, such as privacy, disclosure, and identification, is crucial for ethical polyadic CAs. Future research should also advance usability testing methods and trust-building guidelines for conversational AI.

Virtual Influencers (VIs) are computer-generated characters, many of which are often visually indistinguishable from humans and interact with the world in the first-person perspective as social media influencers. They are gaining popularity by creating content in various areas, including fashion, music, art, sports, games, environmental sustainability, and mental health. Marketing firms and brands increasingly use them to capitalise on their millions of followers. Yet, little is known about what prompts people to engage with these digital beings. In this paper, we present our interview study with online users who followed different VIs on Instagram beyond the fashion application domain. Our findings show that the followers are attracted to VIs due to a unique mixture of visual appeal, sense of mystery, and creative storytelling that sets VI content apart from that of real human influencers. Specifically, VI content enables digital artists and content creators by removing the constraints of bodies and physical features. The followers not only perceived VIs' rising popularity in commercial industries, but also are supportive of VI involvement in non-commercial causes and campaigns. However, followers are reluctant to attribute trustworthiness to VIs in general though they display trust in limited domains, e.g., technology, music, games, and art. This research highlights VI's potential as innovative digital content, carrying influence and employing more varied creators, an appeal that could be harnessed by diverse industries and also by public interest organisations.

Chatbots are regarded as a promising technology for delivering guidance. Prior studies show that chatbots have the potential of coaching users to learn different skills; however, several limitations of chatbot-based approaches remain. People may become disengaged from using chatbot-guided systems and fail to follow the guidance for complex tasks. In this paper, we design chatbots with (HC) and without (OC) human support to deliver guidance for people to practice journaling skills. We conducted a mixed-method study with 35 participants to investigate their actual interaction, perceived interaction, and the effects of interacting with the two chatbots. The participants were randomly assigned to use one of the chatbots for four weeks. Our results show that the HC participants followed the guidance more faithfully during journaling practices and perceived a significantly higher level of engagement and trust with the chatbot system than the OC participants. However, after finishing the journaling-skill training session, the OC participants were more willing to keep using the learned skills than the HC participants. Our work provides new insights into the design of integrating human support into chatbot-based interventions for delivering guidance.

An increasing number of safety departments in organizations across the U.S. are offering mobile apps that allow their local community members to report potential risks, such as hazards, suspicious events, ongoing incidents, and crimes. These "community-sourced risk'' systems are designed for the safety departments to take action to prevent or reduce the severity of situations that may harm the community. However, little is known about the actual use of such community-sourced risk systems from the perspective of both community members and the safety departments. This study is the first large-scale empirical analysis of community-sourced risk systems. More specifically, we conducted a comprehensive system log analysis of LiveSafe--a community-sourced risk system--that has been used by more than two hundred universities and colleges. Our findings revealed a mismatch between what the safety departments expected to receive and what their community members actually reported, and identified several factors (e.g., anonymity, organization, and tip type) that were associated with the safety departments' responses to their members' tips. Our findings provide design implications for chatbot-enabled community-risk systems and make practical contributions for safety organizations and practitioners to improve community engagement.

Causal knowledge is of interest in many areas, such as statistics and machine learning, as it allows people and algorithms to predict outcomes and make data-driven decisions. Researchers in CSCW have proposed tools and workflows to externalize causal knowledge or beliefs from a group of people; however, most of the generated causal diagrams lack a deeper understanding of the causal mechanisms or could not capture diverse beliefs. By integrating narratives with causal diagrams, we implemented an interactive system that allows users to 1) write narratives to rationalize their perceived causal relationships, 2) visualize their causal models using directed diagrams, and 3) review and utilize others' causal diagrams and narratives. We conducted a user study (N=20) to learn how participants leveraged this integrated approach to externalize their perceived causal models for a given application context. Our results showed that the approach implemented in our tool enabled the externalization of users' causal beliefs (e.g., how and why a causal relationship might occur), allowed blind spots of individuals' causal reasoning to be revealed (e.g., learning new ideas from peers), and inspired their causal reasoning (e.g., revising or adding new causal relationships). We also identified the individual differences in people's causal beliefs and observed the impacts of showing others' causal models when one is building his/her causal diagram and narratives. This work provides practical design implications for developing collaborative tools that facilitate capturing and sharing causal beliefs.

Many couples experience long-distance relationships (LDRs), and "couple technologies" have been designed to influence certain relational practices or maintain them in challenging situations. Chatbots show great potential in mediating people's interactions. However, little is known about whether and how chatbots can be desirable and effective for mediating LDRs. In this paper, we conducted a two-phase study to design and evaluate a chatbot, PocketBot, that aims to provide effective interventions for LDRs. In Phase I, we adopted an iterative design process through conducting need-finding interviews to formulate design ideas and piloted the implemented PocketBot with 11 participants. In Phase II, we evaluated PocketBot with eighteen participants (nine LDR couples)in a week-long field trial followed by exit interviews, which yielded empirical understandings of the feasibility, effectiveness, and potential pitfalls of using PocketBot. First, a knock-on-the-door feature allowed couples to know when to resume an interaction after evading a conflict; this feature was preferred by certain participants (e.g., participants with stoic personalities). Second, a humor feature was introduced to spice up couples' conversations. This feature was favored by all participants, although some couples' perceptions of the feature varied due to their different cultural or language backgrounds. Third, a deep talk feature enabled couples at different relational stages to conduct opportunistic conversations about sensitive topics for exploring unknowns about each other, which resulted in surprising discoveries between couples who have been in relationships for years. Our findings provide inspiration for future conversational-based couple technologies that support emotional communication.

Chatbots have great potential to serve as a low-cost, effective tool to support people's self-disclosure. Prior work has shown that reciprocity occurs in human-machine dialog; however, whether reciprocity can be leveraged to promote and sustain deep self-disclosure over time has not been systematically studied. In this work, we design, implement and evaluate a chatbot that has self-disclosure features when it performs small talk with people. We ran a study with 47 participants and divided them into three groups to use different chatting styles of the chatbot for three weeks. We found that chatbot self-disclosure had a reciprocal effect on promoting deeper participant self-disclosure that lasted over the study period, in which the other chat styles without self-disclosure features failed to deliver. Chatbot self-disclosure also had a positive effect on improving participants' perceived intimacy and enjoyment over the study period. Finally, we reflect on the design implications of chatbots where deep self-disclosure is needed over time.

With the proliferation of IoT devices, there are growing concerns about being sensed or monitored by these devices unawares, especially in places perceived as private. We explore the design space of IoT locators to help people physically find nearby IoT devices. We first conducted a survey to understand people's willingness, current practices, and challenges in finding IoT devices. Our survey findings motivated us to design and implement low-cost locators (visual, auditory, and contextualized pictures) to help people find nearby devices. Through an iterative design process and two rounds of experiments, we found that these locators greatly reduced people's search time over a baseline of no locators. Many participants found the visual and auditory locators enjoyable. Some participants also appropriated the use of our system for other purposes, e.g., to learn about new IoT devices, instead of for privacy awareness.

The outbreak of COVID-19 has led to a sharp transition from offline to online education in many countries and areas. This transition heightens the intensity of existing challenges of online education, such as student attendance and education equality. During this time of uncertainty, the vast disparities in teachers? online experience and technical backgrounds, students' education level and their families' economic status, and schools' support, further pose new challenges to teachers and students. In this work, we study how Chinese teachers and students addressed challenges during this transition. We interviewed 15 teachers and 18 students from diverse backgrounds at varying education levels (K-12 and college). Our work makes timely and new contributions to the literature of online education. For example, our results showed that teachers applied Live Video Streaming (LVS) on multiple social media platforms and re-purposed different entertainment features to deliver online teaching for better student engagement; some teachers came to enjoy this new form of instruction after being resistant to it in the beginning, and students developed a better sense of intimacy with their teachers after experiencing certain online interactions. Our work also reveals the remaining challenges and prospects of LVS-based online education and sheds light on the future design of collaborative technologies for online education.

Chatbots are becoming increasingly popular. One promising application for chatbots is to elicit people's self-disclosure of their personal experiences, thoughts, and feelings. As receiving one's deep self-disclosure is critical for mental health professionals to understand people's mental status, chatbots show great potential in the mental health domain. However, there is a lack of research addressing if and how people self-disclose sensitive topics to a real mental health professional (MHP) through a chatbot. In this work, we designed, implemented and evaluated a chatbot that offered three chatting styles; we also conducted a study with 47 participants who were randomly assigned into three groups where each group experienced the chatbot's self-disclosure at varying levels respectively. After using the chatbot for a few weeks, participants were introduced to a MHP and were asked if they would like to share their self-disclosed content with the MHP. If they chose to share, the participants had the option of changing (adding, deleting, and editing) the content they self-disclosed to the chatbot. Comparing participants' self-disclosure data the week before and the week after sharing with the MHP, our results showed that, within each group, the depth of participants' self-disclosure to the chatbot remained after sharing with the MHP; participants exhibited deeper self-disclosure to the MHP through a more self-disclosing chatbot; further, through conversation log analysis, we found that some participants made different edits on their self-disclosed content before sharing it with the MHP. Participants' interview and survey feedback suggested an interaction between participants' trust in the chatbot and their trust in the MHP, which further explained participants' self-disclosure behavior.

A large body of literature is dedicated to understanding people's check-in behavior when they use location sharing services to pair their location with a venue, e.g., a restaurant, a park, etc. Check-in behavior in higher education settings, e.g., where students and instructors have academic purposes for check-ins, is under-studied. In this work, we explore how university students apply two different mechanisms, i.e., automatic and manual location-sharing services, to conduct check-ins for an academic purpose (i.e., students sharing their class attendance with their instructor). More specifically, a Bluetooth Low Energy beacon-based technology is applied to enable automatic class check-ins. We conducted two field trials with a total of 141 university students. Our findings showed that several social, technological, and psychological factors impacted the use of auto and manual check-ins. Feedback from the student participants suggested that future higher education check-in systems may need to consider the integration of check-ins for a variety of purposes.

Danmaku is a new video comment feature that is gaining popularity. Unlike typical forum comments that are displayed with user names below videos, danmaku comments are overlaid on the screen of videos without showing users' information. Prior work studied forum comments and danmaku separately, and little work compared how these two features were used. We collected 38,399 danmaku comments and 16,414 forum comments posted in 2017 on 30 popular videos on Bilibili.com. We examined the usage of these two features in terms of user participation, language used, and ways of sharing knowledge. We found that more users posted danmaku comments, and they also posted these more frequently than forum comments. Even though, in total, more negative language was used in danmaku comments than in forum comments, active users appeared to post more positive comments in danmaku. There was no such correlation in forum comments. It is interesting to find that danmaku and forum comments enabled knowledge sharing in a complementary manner, where danmaku comments involved more explicit knowledge sharing and forum comments exhibited more tacit knowledge sharing. We discuss design implications to promote social interactions for online video systems.

Hearing-impaired people and non-native speakers rely on captions for access to video content, yet most videos remain uncaptioned or have machine-generated captions with high error rates. In this paper, we present the design, implementation and evaluation of BandCaption, a system that combines automatic speech recognition with input from crowd workers to provide a cost-efficient captioning solution for accessible online videos. We consider four stakeholder groups as our source of crowd workers: (i) individuals with hearing impairments, (ii) second-language speakers with low proficiency, (iii) second-language speakers with high proficiency, and (iv) native speakers. Each group has different abilities and incentives, which our workflow leverages. Our findings show that BandCaption enables crowd workers who have different needs and strengths to accomplish micro-tasks and make complementary contributions. Based on our results, we outline opportunities for future research and provide design suggestions to deliver cost-efficient captioning solutions.

Drones pose privacy concerns such as surveillance and stalking. Many technology-based or policy-based mechanisms have been proposed to mitigate these concerns. However, it is unclear how drone controllers and bystanders perceive these mechanisms and whether people intend to adopt them. In this paper, we report results from two rounds of online survey with 169 drone controllers and 717 bystanders in the U.S. We identified respondents' perceived pros and cons of eight privacy mechanisms. We found that owner registration and automatic face blurring individually received most support from both controllers and bystanders. Our respondents also suggested using varied combinations of mechanisms under different drone usage scenarios, highlighting their context-dependent preferences. We outline a set of important questions for future privacy designs and public policies of drones.

Prior research has discovered various privacy concerns that bystanders have about drones. However, little is known about drone controllers' privacy perceptions and practices of drones. Understanding controllers' perspective is important because it will inform whether controllers' current practices protect or infringe on bystanders' privacy and what mechanisms could be designed to better address the potential privacy issues of drones. In this paper, we report results from interviews of 12 drone controllers in the US. Our interviewees treated safety as their top priority but considered privacy issues of drones exaggerated. Our results also highlight many significant differences in how controllers and bystanders think about drone privacy, for instance, how they determine public vs. private spaces and whether notice and consent of bystanders are needed.

The human library is an event intended to engage members of the community in sharing and learning from each other's experiences, and is growing in popularity internationally. Human libraries fall within the larger scope of community knowledge sharing but have received little study and remain largely unsupported by technology. In this study, we examine how community libraries organize and host these events. We present how libraries have attempted to utilize technologies and leverage community support to enable human library events. Our findings reveal inconsistencies in the purpose of human library events, as well as technology applications that are not sufficient to support fully collaborative community knowledge building. We highlight opportunities for increased community participation and technological innovation and also suggest a broader consideration of computer-supported collaborative work in the context of human libraries and experience sharing.

Crowdsourcing platforms such as Amazon Mechanical Turk (MTurk) are widely used by organizations, researchers, and individuals to outsource a broad range of tasks to crowd workers. Prior research has shown that crowdsourcing can pose privacy risks (e.g., de-anonymization) to crowd workers. However, little is known about the specific privacy issues crowd workers have experienced and how they perceive the state of privacy in crowdsourcing. In this paper, we present results from an online survey of 435 MTurk crowd workers from the US, India, and other countries and areas. Our respondents reported different types of privacy concerns (e.g., data aggregation, profiling, scams), experiences of privacy losses (e.g., phishing, malware, stalking, targeted ads), and privacy expectations on MTurk (e.g., screening tasks). Respondents from multiple countries and areas reported experiences with the same privacy issues, suggesting that these problems may be endemic to the whole MTurk platform. We discuss challenges, high-level principles and concrete suggestions in protecting crowd workers'; privacy on MTurk and in crowdsourcing more broadly.

Online Behavioral Advertising (OBA), which involves tracking people's online behaviors, raises serious privacy concerns. We present results from a scenario-based online survey study on American and Chinese Internet users' privacy preferences of OBA. Since privacy is context-dependent, we investigated the effects of country (US vs. China), activity (e.g., online shopping vs. online banking), and platform (desktop/laptop vs. mobile app) on people's willingness to share their information for OBA. We found that American respondents were significantly less willing to share their data and had more specific concerns than their Chinese counterparts. We situate these differences in the broader historical, legal, and social scenes of these countries. We also found that respondents' OBA preferences varied significantly across different online activities, suggesting the potential of context-aware privacy tools for OBA. However, we did not find a significant effect of platform on people's OBA preferences. Lastly, we discuss design implications for privacy tools.

Participatory sensing systems use people and their smartphones as a sensing infrastructure, and getting people to make contributions remains a critical challenge. Little work details how system designers should combine different interactions to increase coverage of service location. Tiramisu, a participatory sensing system, invites transit riders to crowdsource real-time arrival information by sharing location traces when they commute. We extended this system with a new feature that allows riders at stops to "spot" buses passing by. To better understand the impact of this new feature, we conducted an observational log analysis, examining changes in coverage and user behavior before and after the new feature. Following the addition of the spotting feature, participants' contributions increased coverage (the number of trips with real-time data) by 98%, and they used the app more than twice as much. The addition of the spotting feature was also followed by a significant increase of trace contributions.

Abstract Drones are unmanned aircraft controlled remotely or operated autonomously. While the extant literature suggests that drones can in principle invade people’s privacy, little is known about how people actually think about drones. Drawing from a series of in-depth interviews conducted in the United States, we provide a novel and rich account of people’s privacy perceptions of drones for civilian uses both in general and under specific usage scenarios. Our informants raised both physical and information privacy issues against government, organization and individual use of drones. Informants’ reasoning about the acceptance of drone use was in part based on whether the drone is operating in a public or private space. However, our informants differed significantly in their definitions of public and private spaces. While our informants’ privacy concerns such as surveillance, data collection and sharing have been raised for other tracking technologies such as camera phones and closed-circuit television (CCTV), our interviews highlight two heightened issues of drones: (1) powerful yet inconspicuous data collection, (2) hidden and inaccessible drone controllers. These two aspects of drones render some of people’s existing privacy practices futile (e.g., notice recording and ask controllers to stop or delete the recording). Some informants demanded notifications of drones near them and expected drone controllers asking for their explicit permissions before recording. We discuss implications for future privacy-enhancing drone designs.

Effective emotion regulation can benefit many aspects of our lives such as mental health and work performance. Informed by emotion regulation theories and in consultation with our university counseling center, we designed a novel location-based mobile social app, Emotion Map, to help improve people's awareness and regulations of their emotions. The app allows users to log their emotions with the associated time, location, and activity information. Users can keep these logged emotions to themselves or share them with others publicly or anonymously. We conducted a 4-week field trial of the app with 14 university students. Combining usage logs and in-person interviews, our analysis shows promising results of the app. Specifically, we found that the app improved some participants' self-knowledge of their emotions, supported their various emotion regulations, and enabled better awareness of the emotion statuses of their friends and communities.

Current campus communication regarding safety-related issues can be improved for both efficiency and accessibility. We observed a unique opportunity to develop a mobile crowdsourcing system, which allows university community members to report safety related incidents to the campus police department and to share their reports with other users of the system. To better inform the design of such a system, we applied drift-diffusion models in cognitive psychology to model the effect of various factors on users' sharing tendency. We conducted a laboratory experiment with 30 participants. We also ran an MTurk study with 230 participants to explore the feature of anonymous sharing in the application design. In this paper we report various results, including the findings that the time of day, location, and type of crime each affects the likelihood and timeliness of sharing safety reports in several different ways. We also discuss the implications for design of mobile crowdsourcing systems for public safety in general.

Drag and Drop (DnD) web design has been widely used by E-learning systems. However, it may take a lot of effort for web developers who have limited knowledge of web accessibility to build complex keyboard accessible DnD components. In this demo, we present our conceptual design of keyboard accessible DnD, and explain how web developers can leverage the design to implement their own pages. We further discuss how to extend this design to enable different DnD scenarios.

Participatory sensing systems (PSS) require frequent injection of information that has a short shelf-life. The use of crowds to gather information for PSS is therefore particularly challenging. In this study, we explore the impact of two policies on user contributions. A quid-pro-quo policy exchanges contributions from users for access to critical information in the system. A request policy simply reminds the user that information is needed to make the system function well. Prior research has shown that request for help in crowdsourced system is an effective mechanism to increase contributions. During a large-scale experimental study within a publicly deployed, crowdsourced, transit information system, we analyzed metrics associated with frequency of contribution and commitment to long-term use over a 10-month period. Our results confirmed that quid-pro-quo led to more contribution, but at a cost of faster departure from the study. When a participant was simply requested to contribute, but could still access community-generated data if they ignored a request, was largely ineffective and was statistically similar to the control condition where no request for contribution occurred. Thus crowdsource system designers should consider imposing quid-pro-quo type policies for PSS that concentrate on fewer users, but makes them more productive.

Many mobile applications rely on location information gained from location services on mobile devices. However, continuously tracking the device location with high accuracy drains the battery quickly. Furthermore, sensing the same location can be redundant when multiple devices are co-located. In this paper, we develop a crowdsourcing-based location service, E2A2 (energy efficient and accuracy aware), which places colo-cated devices into groups, and uses group location to represent individual device location. The E2A2 location service aims to reduce individual device battery consumption associated with location services while simultaneously maintaining high location accuracy for each device. Our experimental results from a prototype system show the effectiveness of our proposed solution with different mobility patterns. We also present results on the impact of different system parameters and the number of users in a group. Compared to running GPS location services on individual devices separately, our E2A2 service saves on average 33% battery consumption rate when 4 devices are co-located at walking speed and 26% battery consumption rate when 4 devices are colocated on the same bus while meeting the same accuracy requirements.

Crowd-sourcing social computing systems represent a new material for HCI designers. However, these systems are difficult to work with and to prototype, because they require a critical mass of participants to investigate social behavior. Service design is an emerging research area that focuses on how customers co-produce the services that they use, and thus it appears to be a great domain to apply this new material. To investigate this relationship, we developed Tiramisu, a transit information system where commuters share GPS traces and submit problem reports. Tiramisu processes incoming traces and generates real-time arrival time predictions for buses. We conducted a field trial with 28 participants. In this paper we report on the results and reflect on the use of field trials to evaluate crowd-sourcing prototypes and on how crowd sourcing can generate co-production between citizens and public services.

This paper addresses the issue of proxy-based data placement for mobile applications. The key idea is to use aggregated information about mobile users and their data request patterns to determine when, how frequently and how much data to be replicated on proxies. Specifically, we introduce a novel representation, mobile data overlay (MDO) that captures aggregated mobile data access patterns. The underlying representation of the MDO utilizes an interval tree-based data structure in supporting efficient spatio-temporal operations on mobile data access information. We develop intelligent MDO reconfiguration (ReC-MDO) techniques that help determine proper granularity of data replication operation (i.e. appropriate segmentation of each data object) by extracting spatio-temporal locality of mobile data access patterns. The ReC-MDO approach effectively balances tradeoffs between replication cost and data access cost in making mobile data placement decisions on proxies. Through extensive experimentation, we demonstrate the superiority of our techniques over several popular data placement strategies.

The rising popularity of mobile applications and devices has brought about an enhanced interest in infrastructure support for mobile computing. Our work focuses on the development of a mobile grid infrastructure called MAPGrid (mobile applications on Grids), where grid resources are exploited as proxies to enable advanced mobile applications. However, intermittent availability of grid resources presents challenges for data-intensive mobile applications. In this paper, we propose novel methodologies for placing mobile data on grid proxies. We introduce a notion of two-tier architecture for MAPGrid, where the upper tier captures grid related features and the lower tier represents features associated with mobile environments. We further develop an intelligent mobile data placement mechanism that effectively balances tradeoffs between replication cost and data access cost by leveraging knowledge of grid availability and mobile data request patterns. Through extensive experimentation, we illustrate the superiority of the proposed techniques over several popular data placement strategies.

MAPGrid (Mobile APplications on Grids) system enables the delivery of services to mobile users by exploiting heterogenous and intermittently available grid resources. In this paper, we present techniques of cost-effective resource discovery and dynamic resource reprovisioning on grid proxies when context of system environment (e.g. application, network, resource, mobile device) change in infrastructure based wireless networks (e.g. cellular or WLAN). Especially, we focus on how to adapt to dynamic changes of user mobility patterns. We show that the MAPGrid system provides an infrastructure support for enabling and effectively enhancing mobile applications.

In this paper, we propose a novel cache management strategy that uses the notion of "overload" where overload is defined as a situation when there is insufficient proxy cache for a new incoming user in a mobile region. In an overloaded situation, there will be increased network traffic (since the original server will need to be contacted) and increased service delays for mobile hosts (due to cache misses). The proposed techniques attempt to decrease the penalty of overloaded traffic and to reduce the number of remote accesses by increasing cache hit ratio. Our cache replacement algorithm is holistic in that it considers (i) mobility of the clients, (ii) predicted overloads, (iii) sizes of cached objects and (iv) their access frequencies in determining which object's cache (how much cache space) to be replaced, and when to replace. Performance results show that our overload-driven cache management strategy outperforms the existing popular policies

In this paper, we address the problem of resource discovery in a grid based multimedia environment, where the resources providers, i.e. servers, are intermittently available. Given a graph theoretic approach, we define and formulate various policies for QoS-based resource discovery with intermittently available servers that can meet a variety of user needs. We evaluate the performance of these policies under various time-map scenarios and placement strategies. Our performance results illustrate the added benefits obtained by adding flexibility to the scheduling process.