Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10573
Title: Can ChatGPT be Always Powerful: Evidence from a Postgraduate Writing Class
Authors: Lei, Chunlin
Zhu, Dan
Zhang, Junjie
Keywords: CSCL
Issue Date: 2024
Publisher: International Society of the Learning Sciences
Citation: Lei, C., Zhu, D., & Zhang, J. (2024). Can ChatGPT be Always Powerful: Evidence from a Postgraduate Writing Class. In Clarke-Midura, J., Kollar, I., Gu, X., & D'Angelo, C. (Eds.), Proceedings of the 17th International Conference on Computer-Supported Collaborative Learning - CSCL 2024 (pp. 397-398). International Society of the Learning Sciences.
Abstract: This study compared textual features of English compositions produced by a group of Chinese postgraduates and ChatGPT respectively. Quantitative analysis was conducted to investigate the lexical and syntactic complexities, and qualitative analysis was used to examine errors and other textual features. The results showed ChatGPT performed better in creating syntactic variations and error-free texts while postgraduates did better in lexical density and rhetoric use.
Description: Poster
URI: https://doi.org/10.22318/cscl2024.131738
https://repository.isls.org//handle/1/10573
Appears in Collections:ISLS Annual Meeting 2024

Files in This Item:
File SizeFormat 
CSCL2024_397-398.pdf241.74 kBAdobe PDFView/Open


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