Keywords
AI-assisted DWCF
Self-correction awareness
Language proficiency
Published : 2026-08-13
Abstract
The present study aims to compare teacher-led and AI-assisted dynamic written corrective feedback (DWCF) in relation to L2 learners’ self-correction awareness and writing performance. Participants were randomly assigned to the teacher-led DWCF group (N = 51) or the AI-assisted DWCF group (N = 50). A writing pretest was administered before the intervention, and a writing posttest and a questionnaire measuring learners’ self-correction awareness were administered after the intervention. No significant difference was found in self-correction awareness between the teacher-led and AI-assisted DWCF groups, suggesting that both modes can raise learners’ attention to language precision. Moreover, the teacher-led DWCF was more successful than the AI-assisted DWCF in enhancing writing performance. The study argues that AI feedback is more mechanical and superficial than teacher-led corrections. The social interaction in teacher-led DWCF is more likely to ensure comprehensible input, promote deeper thinking, and foster proficiency development. Hence, a combination of teacher-led and AI-assisted DWCF can be the optimal mode in an authentic teaching environment.
References
Hartshorn KJ, Evans NW, Merrill PF, et al., 2010, Effects of Dynamic Corrective Feedback on ESL Writing Accuracy. TESOL Quarterly, 44(1): 84–109.
Evans NW, Hartshorn KJ, McCollum RM, et al., 2010, Contextualizing Corrective Feedback in Second Language Writing Pedagogy. Language Teaching Research, 14(4): 445–463.
Kurzer K, 2018, Dynamic Written Corrective Feedback in Developmental Multilingual Writing Classes. TESOL Quarterly, 52(1): 5–33.
Lee I, 2019, Teacher Written Corrective Feedback: Less Is More. Language Teaching, 52(4): 524–536.
Barrot JS, 2023, Using Automated Written Corrective Feedback in the Writing Classrooms: Effects on L2 Writing Accuracy. Computer Assisted Language Learning, 36(4): 584–607.
Xian L, 2024, Written Corrective Feedback and Individual Differences on Second Language Writing Development. Doctoral dissertation, The Hong Kong Polytechnic University.
Hartshorn KJ, Evans NW, 2012, The Differential Effects of Comprehensive Corrective Feedback on L2 Writing Accuracy. Journal of Linguistics and Language Teaching, 3: 16–46.
Krashen SD, 1985, The Input Hypothesis: Issues and Implications. Longman, New York.
Schmidt RW, 1990, The Role of Consciousness in Second Language Learning. Applied Linguistics, 11(2): 129–158.
Li ZQ, Li YZ, 2019, Research on Second Language Acquisition Input from the Perspective of the Noticing Hypothesis. Journal of Xi’an International Studies University, 27(1): 63–67.
Makino TY, 1993, Learner Self-Correction in EFL Written Compositions. ELT Journal, 47(4): 337–341.
Evans NW, Hartshorn KJ, Strong-Krause D, 2011, The Efficacy of Dynamic Written Corrective Feedback for University-Matriculated ESL Learners. System, 39(2): 229–239.
Su CC, 2024, Role of Artificial Intelligence in Enhancing University English Writing Instruction. Educational Innovations and Emerging Technologies, 4(4): 12–17.
Yang CTY, Chen HHJ, 2026, ChatGPT and L2 Chinese Writing: Evaluating the Impact of Model Version and Prompt Language on Automated Corrective Feedback. Computer Assisted Language Learning, 39(4): 1119–1147.
Crosthwaite P, Sun S, 2026, Generative AI and L2 Written Feedback Studies: A Scoping Review. RELC Journal, 57(1): 207–219.
Lin S, Crosthwaite P, 2024, The Grass Is Not Always Greener: Teacher vs. GPT-Assisted Written Corrective Feedback. System, 127: 103529.