TY - JOUR
T1 - Investigating students’ uptake of teacher- and ChatGPT-generated feedback in EFL writing
T2 - a comparison study
AU - Zou, Shaoyan
AU - Guo, Kai
AU - Wang, Jun
AU - Liu, Yu
N1 - Publisher Copyright:
© 2025 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2025
Y1 - 2025
N2 - While previous studies have compared English as a foreign language (EFL) students’ perceptions of teacher- and ChatGPT-generated feedback on their writing, there remains a gap in understanding how students incorporate feedback from these sources into their revisions. To address this, our study investigated how students use feedback from teachers and ChatGPT in the context of argumentative writing. Twenty Chinese undergraduate students participated in the study, composing argumentative essays, receiving feedback from both teachers and ChatGPT, and revising their essays accordingly. We analyzed their revisions to assess their engagement with the feedback and the appropriateness of their revisions. Additionally, we collected and analyzed their responses to a questionnaire that explored their perceptions and preferences regarding teacher feedback and ChatGPT feedback. The findings revealed that students displayed higher levels of engagement and achieved greater accuracy in their revisions when using teacher feedback. However, an intriguing pattern emerged, indicating that students effectively addressed language and content issues with teacher feedback but showed a particular inclination towards successfully integrating feedback on organization from ChatGPT. Furthermore, the questionnaire results indicated a general preference for teacher feedback while recognizing the unique strengths of ChatGPT feedback, particularly in relation to organization. These findings underscore the potential of using ChatGPT feedback as a complementary resource to teacher feedback. The study demonstrated how these two feedback sources can be synergistically aligned to enhance the overall quality of feedback in EFL writing, promoting a more integrated approach to improve the teaching efficacy of EFL writing.
AB - While previous studies have compared English as a foreign language (EFL) students’ perceptions of teacher- and ChatGPT-generated feedback on their writing, there remains a gap in understanding how students incorporate feedback from these sources into their revisions. To address this, our study investigated how students use feedback from teachers and ChatGPT in the context of argumentative writing. Twenty Chinese undergraduate students participated in the study, composing argumentative essays, receiving feedback from both teachers and ChatGPT, and revising their essays accordingly. We analyzed their revisions to assess their engagement with the feedback and the appropriateness of their revisions. Additionally, we collected and analyzed their responses to a questionnaire that explored their perceptions and preferences regarding teacher feedback and ChatGPT feedback. The findings revealed that students displayed higher levels of engagement and achieved greater accuracy in their revisions when using teacher feedback. However, an intriguing pattern emerged, indicating that students effectively addressed language and content issues with teacher feedback but showed a particular inclination towards successfully integrating feedback on organization from ChatGPT. Furthermore, the questionnaire results indicated a general preference for teacher feedback while recognizing the unique strengths of ChatGPT feedback, particularly in relation to organization. These findings underscore the potential of using ChatGPT feedback as a complementary resource to teacher feedback. The study demonstrated how these two feedback sources can be synergistically aligned to enhance the overall quality of feedback in EFL writing, promoting a more integrated approach to improve the teaching efficacy of EFL writing.
KW - ChatGPT
KW - EFL writing
KW - artificial intelligence
KW - automated writing evaluation
KW - feedback
UR - https://www.scopus.com/pages/publications/85213948102
U2 - 10.1080/09588221.2024.2447279
DO - 10.1080/09588221.2024.2447279
M3 - 文章
AN - SCOPUS:85213948102
SN - 0958-8221
JO - Computer Assisted Language Learning
JF - Computer Assisted Language Learning
ER -