Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/11567| Title: | Developing a Generative AI Framework for Analyzing Student Responses to Enhance Classroom Assessments |
| Authors: | Shin, Namsoo Xing, Yue Qian, Xunlei Krajcik, Joseph |
| Keywords: | Learning Sciences |
| Issue Date: | 2025 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Shin, N., Xing, Y., Qian, X., & Krajcik, J. (2025). Developing a Generative Ai Framework for Analyzing Student Responses to Enhance Classroom Assessments. In Rajala, A., Cortez, A., Hofmann, R., Jornet, A., Lotz-Sisitka, H., & Markauskaite, L. (Eds.), Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025 (pp. 2711-2713). International Society of the Learning Sciences. |
| Series/Report no.: | Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025 |
| Abstract: | This study develops and tests a Large Language Model-based AI framework for analyzing written responses on assessment tasks, generating scoring reasoning, and identifying response uncertainties to provide feedback that supports learning. Using prompt engineering and aggregation methods, the proposed AI models achieved an overall accuracy of 85% when scoring 834 written responses. These findings demonstrate the framework’s potential to enhance the rationale of classroom assessments by providing timely, feedback to improve teaching and learning. |
| Description: | Poster |
| URI: | https://doi.org/10.22318/icls2025.708571 https://repository.isls.org//handle/1/11567 |
| Appears in Collections: | ISLS Annual Meeting 2025 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ICLS2025_2711-2713.pdf | 277.06 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.