Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12761
Title: From talk to evidence: Using conversation-based assessment to elicit scientific reasoning
Other Titles: From Talk to Evidence: Using Conversation-based Assessment to Elicit Scientific Reasoning
Authors: Andrews-Todd, Jessica
Lee, Jeremy
Song, Yi
Ruan, Chunyi
Cisterna, Dante
Forsyth, Carolyn M.
Zapata-Rivera, Diego
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 1308-1312
Publisher: International Society of the Learning Sciences
Citation: Andrews-Todd, J., Lee, J., Song, Y., Ruan, C., Cisterna, D., Forsyth, C. M., & Zapata-Rivera, D. (2026). From talk to evidence: Using conversation-based assessment to elicit scientific reasoning. 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. 1308-1312). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: This study investigated the use of a conversation-based assessment (CBA) on storm formation and prediction to elicit high school students’ scientific reasoning. The task integrates AI-based agents to engage students in interactive dialogue across activities that involved science practices such as data analysis and constructing arguments. Results from a usability study revealed that scores from student-agent conversations, particularly those focused on causal explanation and data interpretation, were significantly associated with students’ final storm prediction performance while traditional item scores were not. Furthermore, analysis of student-agent dialogues showed that the AI agents supported students in revising and improving their responses. These findings highlight the potential of AI-enabled CBAs to surface evidence of scientific reasoning and support student learning and reasoning.
Description: SHORT
URI: https://doi.org/10.22318/icls2026.880928
https://repository.isls.org/handle/1/12761
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_1308-1312.pdf328.93 kBAdobe PDFView/Open


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