Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/13077
Title: AI-scaffolded summarization in STEM: How do students differ in writing and revision?
Other Titles: AI-Scaffolded Summarization in STEM: How do Students Differ in Writing and Revision?
Authors: Han, Hyunkyu
Kim, Seora
Abdeen, Mohamed Shameer
Kim, Min Kyu
Keywords: ICLS
Issue Date: 2026
metadata.dc.format.pagerange: 2852-2854
Publisher: International Society of the Learning Sciences
Citation: Han, H., Kim, S., Abdeen, M. S., & Kim, M. K. (2026). AI-scaffolded summarization in STEM: How do students differ in writing and revision?. 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. 2852-2854). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026
Abstract: Summarization is a key learning strategy in undergraduate STEM, yet students often struggle without timely, effective feedback. This study investigates how an AI-scaffolded feedback system (SMART) relates to students’ revision behaviors and how these patterns vary across diverse student backgrounds. We analyzed 1,081 summary revisions from 49 undergraduates in an introductory physics course using a suite of mixed-effects models. Results show that adding concepts and words while maintaining semantic coherence predicted stronger concept learning, whereas excessive deletion corresponded to weaker outcomes. Revision patterns differed meaningfully by gender, race/ethnicity, and academic level, suggesting that AI-scaffolded feedback needs to be tailored to support diverse learners toward productive revision strategies.
Description: POSTER
URI: https://doi.org/10.22318/icls2026.459142
https://repository.isls.org/handle/1/13077
ISBN: 979-8-9906980-7-9
ISSN: 1819-0138
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
ICLS2026_2852-2854.pdf247.23 kBAdobe PDFView/Open


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