Utilizing Artificial Intelligence to Assess ESL Students' Narratives: A Comparative Analysis
Bibliographic record
Abstract
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.062 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".