International Journal of
Information and Education Technology

Abstract—Student peer code review feedback often does not align with rubric criteria. This reduces its value for learning. This study develops automated methods to classify student peer code review feedback in Bahasa Indonesia. The classification uses seven labels. Six labels represent rubric criteria for code quality in introductory programming courses, namely Variable for naming clarity, Expression for expressions and data types, Control Flow for program logic and exception handling, Comments for code documentation, Layout and Formatting for readability and structure, and Decomposition for modularization and task separation. One additional label captures general feedback. A dataset of 2281 student feedback was created. The data were collected through peer code review activities in an introductory programming course at a higher education institution. The dataset was validated with high agreement between raters (Cohen’s Kappa = 0.9463). Three methods were tested: machine learning, deep learning, and few-shot prompting with large language models. Random Forest with count vectorization gave the best results. It reached an F1-score of 0.9430. This result was higher than that of recurrent convolutional neural networks with FastText embeddings (F1-score = 0.9113) and few-shot prompting (F1-score = 0.852). The results show that classical machine learning with token features can be more effective than complex models. These findings provide a foundation for integrating automated classification into peer code review tools, supporting more consistent, rubric-based feedback in computing education.

Keywords—student peer code review, rubric-based classification, machine learning, deep learning, few-shot prompting, computing education, Bahasa Indonesia

[PDF]

Cite: Theresia Devi Indriasari and Yohanes Sigit Purnomo W.P., "Automated Rubric-Based Classification of Student Peer Code Review Feedback," International Journal of Information and Education Technology, vol. 16, no. 5, pp. 1298-1314, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).