Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/11658| Title: | Exploring the Use of Generative AI to Identify ‘Coachable Moments’ in Classroom Discussions |
| Authors: | Matsumura, Lindsay Clare Walsh, Marguerite Li, Tianwen Correnti, Rip Litman, Diane |
| Keywords: | Learning Sciences |
| Issue Date: | 2025 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Matsumura, L. C., Walsh, M., Li, T., Correnti, R., & Litman, D. (2025). Exploring the Use of Generative Ai to Identify ‘Coachable Moments’ in Classroom Discussions. 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. 2971-2972). International Society of the Learning Sciences. |
| Series/Report no.: | Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025 |
| Abstract: | Our study explores the potential of generative AI (ChatGPT 4) to select segments from classroom text discussion to support a productive professional learning conversation. We compare the quality of segments chosen by GPT 4 to those chosen by an expert coach. Results show that nearly half (43%) of the GPT selected segments are of a similar quality to those chosen by the expert coach. An additional quarter are close to this level of quality. |
| Description: | Poster |
| URI: | https://doi.org/10.22318/icls2025.344821 https://repository.isls.org//handle/1/11658 |
| Appears in Collections: | ISLS Annual Meeting 2025 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ICLS2025_2971-2972.pdf | 228.45 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.