Conference Agenda (All times are shown in Eastern Daylight Time)

Generative artificial intelligence (GenAI) is rapidly transforming how human beings perform cognitive and creative tasks, including the strategies they employ in seeking information. Freed from the constraints that have traditionally shaped query formulation in traditional query-response information retrieval (IR) systems, GenAI users employ novel strategies—framing commands in natural language, embedding personal details, and experimenting with conversational approaches. Drawing on information-seeking research in library and information science (LIS), the present study examines the structure and defining features of these human–GenAI interactions, revealing notable parallels with Belkin’s (1980) Cognitive Communication System for Information Retrieval. In doing so, it underscores essential implications for contemporary information retrieval in an era of expanding global GenAI adoption.

This paper reports on the use of chatbots among US-based, national sexual assault and domestic violence hotlines, and examines how these chatbots are conceptualized. Because chatbots are indifferent to their outputs but survivors in crisis/danger require trauma-informed, empathetic support, it is important to understand how hotlines conceptualize their chatbots and present them to survivors. Through qualitative content analysis of supporting documentation about the chatbots, this project found that the hotlines describe similar purposes of the chatbots and state the chatbots are not replacements for live services. However, the hotlines diverge in how they refer to the chatbots (“it” vs. “she” / “digital friend”) and in what features the chatbot offers. The use of “she” and “digital friend,” and the knowledge and skills required by some features of the chatbots blur the line between the chatbot being a simple, information retrieval tool and human-like enough to replace trained, live support.

Palliative care is frequently misunderstood, yet short videos on social media can help disseminate useful information and build supportive communities. One major challenge is that manually analyzing such content is labor-intensive and time-consuming. Meanwhile, large language models (LLMs) show promise for automated content analysis, but their domain-specific accuracy in this sensitive area remains uncertain. In this study, we propose an iterative LLM-LLM agentic conversational approach to identify palliative care themes from 56 TikTok videos. We collected video transcripts, metadata, visual labels, and on-screen text to build a multimodal dataset. Through iterative dialogues between two LLMs, we generated initial themes and refined them via human feedback to address missed dimensions. Our approach identified themes such as Policy, Advocacy, and Access, as well as Emotional Support and Coping while highlighting omissions like Humor and Saying Goodbye, underlining the need for human oversight. Our findings reveal that LLM-driven automation can reduce annotation workload, but it has limitations in capturing emotional content. The contributions of this work include a new annotated dataset of 242 TikTok videos, a validated LLM-based thematic analysis pipeline, and evidence that combining automated and human-in-the-loop methods enhances reliability and accuracy in short-form video analysis.