MétaCan
Menu
Back to cohort
Record W4415387478 · doi:10.5430/wjel.v16n2p258

Examining the Efficacy of ChatGPT and Human-Derived Corrective Feedback in Addressing Grammatical Errors in Saudi EFL Students' Compositions

2025· article· W4415387478 on OpenAlexvenueno aff
Fawaz Al Mahmud

Bibliographic record

VenueWorld Journal of English Language · 2025
Typearticle
Language
FieldComputer Science
TopicIntelligent Tutoring Systems and Adaptive Learning
Canadian institutionsnot available
FundersUniversity of Jeddah
KeywordsCorrective feedbackAffordanceCompetence (human resources)PerceptionControl (management)Linguistic competencePeer feedbackGrammar

Abstract

fetched live from OpenAlex

Employing an explanatory mixed-methods approach, this study compared the affordances of ChatGPT’s written corrective feedback (WCF) and human corrective feedback in fostering linguistic accuracy among Saudi EFL learners. Participants were 53 undergraduates at the University of Jeddah, divided into an experimental group (n = 26) and a control group (n = 27). Over eight weeks, both groups engaged in two 1.5-hour writing sessions per week. The experimental group received WCF from ChatGPT, while the control group received human WCF. Pretests and posttests assessed participants’ grammatical competence before and after the intervention. Error-flagging accuracy was evaluated by a panel of experienced university teachers of English. Semi-structured interviews with six experimental-group participants explored perceptions of ChatGPT. Quantitative findings indicated that ChatGPT was a more effective source of WCF than human feedback, as the experimental group significantly outperformed the control group in the posttest. However, human feedback was slightly more accurate in error-flagging. Qualitative results revealed that most students valued ChatGPT for its precise error identification, though some considered human feedback clearer in explanation. The study concludes that ChatGPT can serve as a valuable supplementary tool for corrective feedback in Saudi EFL writing.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.647
Threshold uncertainty score0.905

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.028
GPT teacher head0.315
Teacher spread0.287 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueWorld Journal of English LanguageSame topicIntelligent Tutoring Systems and Adaptive LearningFrench-language works237,207