Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework
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.
Authors
- Jessie Saraza Barrot (ORCID: https://orcid.org/0000-0001-8517-4058)
Institutions
- Ton Duc Thang University (VN)
- National University (PH)
Publication Details
- Journal
- RELC Journal
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1177/00336882261505634
- Primary Topic
- Artificial Intelligence in Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00