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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework

Jessie Saraza Barrot
4 links
RELC Journal
Artificial Intelligence in Education
article

Generative AI for automated essay scoring in writing classrooms: A thematic review using CIMO framework

Jessie Saraza Barrot
article en

Abstract

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.

RELC Journal
Ton Duc Thang University (VN), National University (PH)
Quality education
Artificial Intelligence in Education
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.

Laika access coming soon