Code Review Automation: Strengths and Weaknesses of the State of the Art
Top Cited Papers
- 1 January 2024
- journal article
- review article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (2) , 338-353
Abstract
The automation of code review has been tackled by several researchers with the goal of reducing its cost. The adoption of deep learning in software engineering pushed the automation to new boundaries, with techniques imitating developers in generative tasks, such as commenting on a code change as a reviewer would do or addressing a reviewer’s comment by modifying code. The performance of these techniques is usually assessed through quantitative metrics, e.g. , the percentage of instances in the test set for which correct predictions are generated, leaving many open questions on the techniques’ capabilities. For example, knowing that an approach is able to correctly address a reviewer’s comment in 10% of cases is of little value without knowing what was asked by the reviewer: What if in all successful cases the code change required to address the comment was just the removal of an empty line? In this paper we aim at characterizing the cases in which three code review automation techniques tend to succeed or fail in the two above-described tasks. The study has a strong qualitative focus, with ~105 man-hours of manual inspection invested in manually analyzing correct and wrong predictions generated by the three techniques, for a total of 2,291 inspected predictions. The output of this analysis are two taxonomies reporting, for each of the two tasks, the types of code changes on which the experimented techniques tend to succeed or to fail, pointing to areas for future work. A result of our manual analysis was also the identification of several issues in the datasets used to train and test the experimented techniques. Finally, we assess the importance of researching in techniques specialized for code review automation by comparing their performance with ChatGPT, a general purpose large language model, finding that ChatGPT struggles in commenting code as a human reviewer would do.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot2023
- Data Augmentation by Program TransformationJournal of Systems and Software, 2022
- Towards Automating Code Review Activities2021
- WhoReview: A multi-objective search-based approach for code reviewers recommendation in modern code reviewApplied Soft Computing, 2021
- Who should make decision on this pull request? Analyzing time-decaying relationships and file similarities for integrator predictionJournal of Systems and Software, 2019
- On Learning Meaningful Code Changes Via Neural Machine Translation2019
- Who should comment on this pull request? Analyzing attributes for more accurate commenter recommendation in pull-based developmentInformation and Software Technology, 2017
- Reviewer recommendation for pull-requests in GitHub: What can we learn from code review and bug assignment?Information and Software Technology, 2016
- Impact of Peer Code Review on Peer Impression Formation: A Survey2013
- Expectations, outcomes, and challenges of modern code review2013