Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12593
Title: Analyzing human–AI interaction patterns in generative-AI-supported inquiry-based learning
Other Titles: Analyzing Human–AI Interaction Patterns in Generative-AI-Supported Inquiry-Based Learning
Authors: Ohsaki, Ayano
Matsukawa, Hideya
Egusa, Ryohei
Takahashi, Satoshi
Keywords: CSCL
Issue Date: 2026
metadata.dc.format.pagerange: 788-790
Publisher: International Society of the Learning Sciences
Citation: Ohsaki, A., Matsukawa, H., Egusa, R., & Takahashi, S. (2026). Analyzing human–AI interaction patterns in generative-AI-supported inquiry-based learning. In Rosé, C., Gweon, G., Asterhan, C., & Keune, A. (Eds.), Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026 (pp. 788-790). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026
Abstract: This study contributes to computer-supported collaborative learning research by examining human–artificial intelligence (AI) dialogue patterns across teams with different experience levels with generative AI (GAI)-supported inquiry-based learning. Epistemic network analysis of dialogues from 26 teams reveals that teams using GAI support for the second time exhibit projective actions toward their goals through active questioning and concept clarification. In contrast, inexperienced teams rely on GAI scaffolding with passive responses. Notably, goal-oriented questions emerge as critical mediators connecting different question types among first-time user teams.
Description: POSTER
URI: https://doi.org/10.22318/cscl2026.589711
https://repository.isls.org/handle/1/12593
ISBN: 979-8-9906980-6-2
ISSN: 2543-0157
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
CSCL2026_788-790.pdf254.94 kBAdobe PDFView/Open


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