Please use this identifier to cite or link to this item: https://repository.isls.org//handle/1/10177
Title: Can AI Help Teachers Write Higher Quality Feedback? Lessons Learned From Using the GPT-3 Engine in a Makerspace Course
Authors: Sung, Gahyun
Guillain, Léonore
Schneider, Bertrand
Keywords: Learning Sciences
Issue Date: 2023
Publisher: International Society of the Learning Sciences
Citation: Sung, G., Guillain, L., & Schneider, B. (2023). Can AI help teachers write higher quality feedback? Lessons learned from using the GPT-3 engine in a makerspace course. In Blikstein, P., Van Aalst, J., Kizito, R., & Brennan, K. (Eds.), Proceedings of the 17th International Conference of the Learning Sciences - ICLS 2023 (pp. 2093-2094). International Society of the Learning Sciences.
Abstract: We explore how a cutting-edge language model, GPT-3, can be used to augment and assist periodic feedback writing in a makerspace course. Personalized messages were generated using student data then edited and combined with human instructor feedback. We discuss the lessons learned: namely, AI did well in summarizing work and positive encouragements, yet could write off-target feedback for struggling students. An initial interview with an instructor revealed that future iterations must consider ways to formalize and manage human expert roles.
Description: Poster
URI: https://doi.org/10.22318/icls2023.904961
https://repository.isls.org//handle/1/10177
Appears in Collections:ISLS Annual Meeting 2023

Files in This Item:
File SizeFormat 
ICLS2023_2093-2094.pdf137.64 kBAdobe PDFView/Open


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