Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12775
Title: Design and perceptions of a science conversation-based assessment with AI agents
Other Titles: Design and Perceptions of a Science Conversation-based Assessment with AI Agents
Authors: Andrews-Todd, Jessica
Lee, Jeremy
Cisterna, Dante
Song, Yi
Graf, Edith Aurora
Jiang, Yang
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 1378-1382
Publisher: International Society of the Learning Sciences
Citation: Andrews-Todd, J., Lee, J., Cisterna, D., Song, Y., Graf, E. A., & Jiang, Y. (2026). Design and perceptions of a science conversation-based assessment with AI agents. 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. 1378-1382). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: Conversation-based assessments (CBAs) incorporate conversational agents into computer-based tasks to elicit evidence about learners’ knowledge and skills in a domain. We describe the design of a science conversation-based assessment incorporating AI agents that engages high school students in a scenario related to storm formation and storm prediction. We further discuss results from a usability study in which students completed the CBA task and subsequently responded to interview questions about their perceptions related to the design and usability of the task. Students generally had positive experiences with the task and its design, though challenges related to information clarity and AI interaction authenticity were noted.
Description: SHORT
URI: https://doi.org/10.22318/icls2026.586385
https://repository.isls.org/handle/1/12775
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_1378-1382.pdf329.18 kBAdobe PDFView/Open


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