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.

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.

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.

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.

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).

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.