MétaCan
Menu
Back to cohort
Record W4410905008 · doi:10.63332/joph.v5i6.2224

Utilizing Artificial Intelligence to Assess ESL Students' Narratives: A Comparative Analysis

2025· article· en· W4410905008 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Posthumanism · 2025
Typearticle
Languageen
FieldHealth Professions
TopicDigital Storytelling and Education
Canadian institutionsFoothills Medical Centre
Fundersnot available
KeywordsNarrativePsychologyMathematics educationArtificial intelligenceComputer scienceLinguistics

Abstract

fetched live from OpenAlex

This study investigates the effectiveness, reliability, and potential biases of AI-based assessment tools in evaluating narrative essays written by undergraduate ESL students at a Saudi university. A total of 30 essays were assessed using a detailed rubric covering five writing components: ideas and content, organization, vocabulary, voice and style, and mechanics and formatting. The essays were graded by human evaluators and five AI tools—ChatGPT, Gemini, Claude, Justdone, and Chatsonic. A quantitative comparative research design was employed, and statistical analyses, including one-way ANOVA and correlation tests, were conducted to examine grading consistency and divergence. Results revealed that AI tools aligned more closely with human graders on objective criteria like mechanics and formatting, but showed significant discrepancies in subjective aspects such as voice and style. The study highlights the potential of AI to support human grading but underscores the importance of human oversight to ensure fairness and contextual sensitivity in ESL writing assessment.

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.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.250
Threshold uncertainty score0.429

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.248
GPT teacher head0.534
Teacher spread0.286 · 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