L2 Spanish and Indonesian learners’ engagement with ChatGPT written corrective feedback

Written corrective feedback (WCF) plays a crucial role in second language (L2) writing by helping learners address local (grammar) and global (content) errors (Crosthwaite et al., 2021). The rise of Generative Artificial Intelligence (GenAI) has increased interest in its role in WCF; Tools such as ChatGPT can provide personalised feedback by explaining grammar, defining words and translating between languages (Kohnke et al., 2023). However, studies have focused exclusively on English (Lin & Crosthwaite, 2024), limiting the linguistic inclusivity in the research. In addition, despite the recognised importance of learner engagement for the effectiveness of WCF, only a few studies (Koltovskaia et al., 2024; Zhang & Hyland, 2022) have examined learners' engagement with WCF; however, little is known about the follow-up questions students may ask regarding the feedback they receive. This study applies a multidimensional framework of learner engagement (Zhang & Hyland, 2018) to analyse how 13 intermediate L2 learners of Spanish and Indonesian engaged cognitively, behaviorally and attitudinally with ChatGPT’s feedback. Participants wrote a short L2 essay on their reasons for learning a L2 and then used a pre-prepared prompt to seek WCF from ChatGPT. A semi-structured interview followed this. Students’ drafts, revisions and follow-up questions were coded for behavioural and cognitive engagement. The interview data were analysed thematically for cognitive and attitudinal engagement. Spanish and Indonesian students noticed most WCF at local and global levels, but relied more on ChatGPT for the former. While participants found ChatGPT’s feedback mostly useful, they remained critical of its relevance and accuracy. These findings highlight that while ChatGPT could offer accessible WCF, its effectiveness depends on learners’ ability to critically evaluate it. The study shows the opportunities and challenges of integrating GenAI for WCF, broadening the understanding of how diverse linguistic communities engage with technology for L2 writing.

Authors

Institutions

Publication Details

Journal
Proceedings of the International CALL Research Conference
Published
2025-09-30
DOI
https://doi.org/10.29140/97817637116240-05
Primary Topic
Text Readability and Simplification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

L2 Spanish and Indonesian learners’ engagement with ChatGPT written corrective feedback

Franciele Spinelli, Alicia Gazmuri Sanhueza, David Wijaya
Proceedings of the International CALL Research Conference
Text Readability and Simplification
article

L2 Spanish and Indonesian learners’ engagement with ChatGPT written corrective feedback

Franciele Spinelli, Alicia Gazmuri Sanhueza, David Wijaya
article en

Abstract

Written corrective feedback (WCF) plays a crucial role in second language (L2) writing by helping learners address local (grammar) and global (content) errors (Crosthwaite et al., 2021). The rise of Generative Artificial Intelligence (GenAI) has increased interest in its role in WCF; Tools such as ChatGPT can provide personalised feedback by explaining grammar, defining words and translating between languages (Kohnke et al., 2023). However, studies have focused exclusively on English (Lin & Crosthwaite, 2024), limiting the linguistic inclusivity in the research. In addition, despite the recognised importance of learner engagement for the effectiveness of WCF, only a few studies (Koltovskaia et al., 2024; Zhang & Hyland, 2022) have examined learners' engagement with WCF; however, little is known about the follow-up questions students may ask regarding the feedback they receive. This study applies a multidimensional framework of learner engagement (Zhang & Hyland, 2018) to analyse how 13 intermediate L2 learners of Spanish and Indonesian engaged cognitively, behaviorally and attitudinally with ChatGPT’s feedback. Participants wrote a short L2 essay on their reasons for learning a L2 and then used a pre-prepared prompt to seek WCF from ChatGPT. A semi-structured interview followed this. Students’ drafts, revisions and follow-up questions were coded for behavioural and cognitive engagement. The interview data were analysed thematically for cognitive and attitudinal engagement. Spanish and Indonesian students noticed most WCF at local and global levels, but relied more on ChatGPT for the former. While participants found ChatGPT’s feedback mostly useful, they remained critical of its relevance and accuracy. These findings highlight that while ChatGPT could offer accessible WCF, its effectiveness depends on learners’ ability to critically evaluate it. The study shows the opportunities and challenges of integrating GenAI for WCF, broadening the understanding of how diverse linguistic communities engage with technology for L2 writing.

Proceedings of the International CALL Research ConferenceVol. 2025
The University of Sydney (AU), The University of Queensland (AU)
Openalex Percentile: Top 85%
Text Readability and Simplification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.