ISLS 2026
ICLS Poster

#163: Understanding the Effects of LLM-Generated Conversation Initiations with Learners in Popular Science Video-Based Learning

Thu Jun 18, 4:15 PM–5:45 PM · Outdoors

Recent breakthroughs in large language models (LLMs) make it possible to create learning companion agents that boost the interactivity in video-based learning. This study focuses on learning companion agents’ role as conversation initiators. How do different styles of agents’ conversation initiation influence learners’ learning experiences? We conducted a controlled experiment (N=65) using a technology probe that sends varying types of conversation initiation messages to learners. We reveal how the personas and message styles of learning companion agents shape learners’ experiences.

Speakers

  • Jingchao Fang — University of Chicago
  • Hao-Chuan Wang — University of California, Davis

Authors

Jingchao Fang, Qingxiaoyang Zhu, Hao-Chuan Wang