Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/13001
Title: Understanding the effects of LLM-generated conversation initiations with learners in popular science video-based learning
Other Titles: Understanding the Effects of LLM-Generated Conversation Initiations with Learners in Popular Science Video-Based Learning
Authors: Fang, Jingchao
Zhu, Qingxiaoyang
Wang, Hao-Chuan
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 2624-2626
Publisher: International Society of the Learning Sciences
Citation: Fang, J., Zhu, Q., & Wang, H. (2026). Understanding the effects of LLM-generated conversation initiations with learners in popular science video-based learning. In Litts, B. K., DeLiema, D., Lee, C., Krist, S. Mawasi, A., Martin, L., & Kumpulainen, K. (Eds.), Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026 (pp. 2624-2626). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: 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.
Description: POSTER
URI: https://doi.org/10.22318/icls2026.131385
https://repository.isls.org/handle/1/13001
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_2624-2626.pdf213.64 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.