Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework
RELC Journal · 13.11.2026
DOI: 10.1177/00336882261505634 ↗Kurz gefasst
Fachartikel in der Zeitschrift RELC Journal, online erschienen am 13.11.2026. Verfasst von Jessie S Barrot. Die Arbeit nennt 16 Literaturangaben. Gefördert von: Ton Duc Thang University, Vietnam.
Abstract (Originalsprache)
This study reviewed empirical research on generative artificial intelligence (GenAI)–based automated scoring using the Context–Intervention–Mechanism–Outcome framework. Descriptive quantitative evidence mapping synthesized findings from 47 studies published between 2023 and 2025. The results showed that research focused largely on tertiary English as a Second or Foreign Language context and English academic writing, with rubric-based and hybrid human–artificial-intelligence scoring models dominating current practice. Evidence indicates that several studies reported substantial agreement with human raters, while individual studies also described improvements in scoring efficiency and feedback delivery. However, reliability remained sensitive to several factors, and concerns persisted regarding score instability, higher-order writing assessment, fairness, transparency, and ethics. The review suggests that GenAI-based scoring has substantial potential but also presents important risks that require careful implementation and thorough consideration of its implications.
Förderung
- Ton Duc Thang University, Vietnam
Zitieren
APA
Barrot, J. S. (2026). Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework. RELC Journal. https://doi.org/10.1177/00336882261505634
Vancouver
Barrot JS. Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework. RELC Journal. 2026. doi:10.1177/00336882261505634
BibTeX
@article{Barrot2026,
author = {Barrot, Jessie S},
title = {Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework},
journal = {RELC Journal},
year = {2026},
doi = {10.1177/00336882261505634}
}
EUVIMED