Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12486
Title: Combining collaborative and adaptive learning: Constructive–interactive engagement through concept maps, teachable agents, and an adaptive tutor
Other Titles: Combining Collaborative and Adaptive Learning: Constructive–Interactive Engagement through Concept Maps, Teachable Agents, and an Adaptive Tutor
Authors: Hayashi, Yugo
Shimojo, Shigen
Koedinger, Kenneth R.
Keywords: CSCL
Issue Date: 2026
metadata.dc.format.pagerange: 349-353
Publisher: International Society of the Learning Sciences
Citation: Hayashi, Y., Shimojo, S., & Koedinger, K. R. (2026). Combining collaborative and adaptive learning: Constructive–interactive engagement through concept maps, teachable agents, and an adaptive tutor. In Rosé, C., Gweon, G., Asterhan, C., & Keune, A. (Eds.), Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026 (pp. 349-353). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026
Abstract: Integrating intelligent tutoring systems (ITS) with computer-supported collaborative learning (CSCL) may support deeper learning by combining adaptive feedback with collaborative knowledge construction. This study examined whether integrating adaptive and collaborative supports promotes constructive–interactive engagement. Seventy-four university students participated in an experiment comparing three conditions: ITS-only (adaptive), concept map construction with a teachable agent (collaborative), and a hybrid condition combining both supports. Learning was measured using pre- and posttests, and collaborative processes were examined through concept maps and verbal interaction measures. Results showed that the hybrid condition achieved the highest learning gains, while adaptive support alone produced higher comprehension than collaborative support alone. Process measures showed no significant differences across conditions, suggesting that the hybrid condition maintained comparable levels of collaboration despite additional individual tasks. These findings suggest that integrating adaptive and collaborative supports can effectively support deeper learning in CSCL environments.
Description: SHORT
URI: https://doi.org/10.22318/cscl2026.518924
https://repository.isls.org/handle/1/12486
ISBN: 979-8-9906980-6-2
ISSN: 2543-0157
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
CSCL2026_349-353.pdf364.18 kBAdobe PDFView/Open


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