The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N = 8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N = 18) and crowdsourced evaluation (N = 100) demonstrate that PaperTok’s workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach.

Student feedback is critical for improving teaching, yet instructors often avoid reading evaluations due to emotional burden and information overload. We present a systematic exploration of how language models can distill and transform student evaluations into adaptive, actionable insights. Through a systematic design space exploration combining 4 feedback strategies (removing harmful content, paraphrasing criticism, sandwiching negatives, adding constructive suggestions) with 4 presentation formats (themes, cards, letters, chatbots), we created six AI-augmented prototypes of teaching evaluations. Interviews with 16 post-secondary instructors revealed that effective use of AI in feedback processing should: (1) support action formation through focused views and divergent thinking, (2) reduce emotional costs while enabling celebration and sharing, (3) facilitate longitudinal engagement and re-contextualization across terms, and (4) maintain transparency and preserve access to original context to build trust. Our work provides design guidelines for AI-augmented feedback systems and demonstrates how language models can adaptively process and present information based on feedback receivers' specific needs and contexts.

Trust is not just a cognitive issue but also an emotional one, yet the research in human-AI interactions has primarily focused on the cognitive route of trust development. Recent work has highlighted the importance of studying affective trust towards AI, especially in the context of emerging human-like LLM-powered conversational agents. However, there is a lack of validated and generalizable measures for the two-dimensional construct of trust in AI agents. To address this gap, we developed and validated a set of 27-item semantic differential scales for affective and cognitive trust through a scenario-based survey study. We then further validated and applied the scale through an experiment study. Our empirical findings showed how the emotional and cognitive aspects of trust interact with each other and collectively shape a person's overall trust in AI agents. Our study methodology and findings also provide insights into the capability of the state-of-art LLMs to foster trust through different routes.

Data analysis is challenging as it requires synthesizing domain knowledge, statistical expertise, and programming skills. Assistants powered by large language models (LLMs), such as ChatGPT, can assist analysts by translating natural language instructions into code. However, AI-assistant responses and analysis code can be misaligned with the analyst’s intent or be seemingly correct but lead to incorrect conclusions. Therefore, validating AI assistance is crucial and challenging. Here, we explore how analysts understand and verify the correctness of AI-generated analyses. To observe analysts in diverse verification approaches, we develop a design probe equipped with natural language explanations, code, visualizations, and interactive data tables with common data operations. Through a qualitative user study (n=22) using this probe, we uncover common behaviors within verification workflows and how analysts’ programming, analysis, and tool backgrounds reflect these behaviors. Additionally, we provide recommendations for analysts and highlight opportunities for designers to improve future AI-assistant experiences.

Many people gather online and form teams with strangers to collaborate on tasks. However, while intrateam trust and cohesion are critical for team performance, such characteristics take time to establish and are harder to build up through computer-mediated communication. Building on prior research that has shown that enhancing familiarity between members can help, we hypothesized that the use of a chatbot to support the familiarization of ad hoc teammates can help their collaboration. As such, we designed IntroBot, a chatbot that builds on an online discussion facilitator framework and leverages the social media data of users to assist their familiarization process. Through a between-subjects study (N=60), we found that participants who used IntroBot reported higher levels of trust, cohesion, and interaction quality, as well as generated more ideas in a collaborative brainstorming task. We discuss insights gained from our study, and present opportunities for the future of chatbot-assisted collaboration.

ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) is considered one of the premium forums for research on accessibility. Recently, Mack et al. shed light on the demographics, goals, research methodologies, and evolution of accessibility research over time. We extend their work by exploring the frequencies and trends of disability categories and computer science research domains in publications at ASSETS (N=1,678). Our results show that disability categories and research domains varied significantly across the publication years. We found that in the past 10 years, publications targeting Mental-Health-Related disabilities and the research domain of AR/VR show an increasing trend. In opposition, Gaming, Input Methods/Interaction Techniques, and User Interfaces domains portray a decreasing trend. Additionally, our results show that the majority of the publications utilize the AI/ML/CV/NLP domain (19%) and focus on people with visual disabilities (42%). We share our preliminary exploration results and identify avenues for future work.