Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11249
Title: Feedback Sources in Argumentative Writing: AI Feedback or Peer Feedback?
Authors: Ji, Jiaojiao
Zhao, Hengxuan
Wu, Yong
Keywords: Learning Sciences
Issue Date: 2025
Publisher: International Society of the Learning Sciences
Citation: Ji, J., Zhao, H., & Wu, Y. (2025). Feedback Sources in Argumentative Writing: Ai Feedback or Peer Feedback?. 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. 1242-1246). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025
Abstract: This study compared AI feedback with peer feedback, examining both the quantity and qualitative aspects of negative feedback. The results indicated that ChatGPT (the AI tool used in the study) generated a consistent volume of feedback across various dimensions, contrasting with the variable amounts observed in peer feedback. Quantitatively, ChatGPT produced more negative feedback than peers. Qualitatively, it provided more mitigating praises and general suggestions for issues related to both essay content and form, as well as more specific solutions for form-focused issues. However, peer feedback excelled in offering more detailed explanations for content-related issues. The implications of the research findings are discussed.
Description: Short Paper
URI: https://doi.org/10.22318/icls2025.384467
https://repository.isls.org//handle/1/11249
Appears in Collections:ISLS Annual Meeting 2025

Files in This Item:
File SizeFormat 
ICLS2025_1242-1246.pdf273.98 kBAdobe PDFView/Open


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