Implementation of Git&#039;s Commit Message Classification Model Using GPT-Linked Source Change Data (GPT 연계 소스변경 데이터를 활용한 깃의 커밋 메시지 분류 모델 구현에 관한 연구)

Ji-Hoon Choi (최지훈); Kim Jae Woong (김재웅); Seong-Hyun Park (박성현)

doi:10.9708/jksci.2023.28.10.123

Implementation of Git's Commit Message Classification Model Using GPT-Linked Source Change Data

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2023, 28(10), pp.123-132
DOI : 10.9708/jksci.2023.28.10.123
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : September 1, 2023
Accepted : October 12, 2023
Published : October 31, 2023

Ji-Hoon Choi ¹, Kim Jae Woong ², Seong-Hyun Park ³

¹공주대학교 컴퓨터공학과
²공주대학교
³공주대학교 컴퓨터공학과 박사과정

Accredited

ABSTRACT

Git's commit messages manage the history of source changes during project progress or operation. By utilizing this historical data, project risks and project status can be identified, thereby reducing costs and improving time efficiency. A lot of research related to this is in progress, and among these research areas, there is research that classifies commit messages as a type of software maintenance. Among published studies, the maximum classification accuracy is reported to be 95%. In this paper, we began research with the purpose of utilizing solutions using the commit classification model, and conducted research to remove the limitation that the model with the highest accuracy among existing studies can only be applied to programs written in the JAVA language. To this end, we designed and implemented an additional step to standardize source change data into natural language using GPT. This text explains the process of extracting commit messages and source change data from Git, standardizing the source change data with GPT, and the learning process using the DistilBERT model. As a result of verification, an accuracy of 91% was measured. The proposed model was implemented and verified to ensure accuracy and to be able to classify without being dependent on a specific program. In the future, we plan to study a classification model using Bard and a management tool model helpful to the project using the proposed classification model.

KEYWORDS

Commit Message, GPT, Source Change, DistilBERT, Multi-Label Classification

Citation status

* References for papers published after 2023 are currently being built.

[confproc] Heričko, T. / 2023 / Commit classification into software maintenance activities: A systematic literature review / 2023IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC) IEEE : 1646~1651

[confproc] T. Heričko / 2023 / Automatic data-driven software change identification via code representation learning / Proceedings of the International Conference on Evaluation and Assessment in Software Engineering

[confproc] Mockus / 2000 / Identifying reasons for software changes using historic databases / Proceedings 2000 International Conference on Software Maintenance : 120~130

[confproc] S. Gharbi / 2019 / On the Classification of Software Change Messages Using Multi-Label Active Learning / Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing : 1760~1767

[journal] Harald C. Gall / 2009 / Change Analysis with Evolizer and ChangeDistiller / IEEE Software / Institute of Electrical and Electronics Engineers (IEEE) 26(1) : 26~33

[confproc] B. Fluri / 2008 / Discovering patterns of change types / Automated Software Engineering, 2008. ASE 2008. 23rd IEEE/ACM International Conference on / IEEE : 463~466

[web] M. Martinez / 2013 / Automatically extracting instances of code change patterns with ast analysis / arXiv / arXiv:1309.3730

[journal] Beat Fluri / 2007 / Change Distilling:Tree Differencing for Fine-Grained Source Code Change Extraction / IEEE Transactions on Software Engineering / Institute of Electrical and Electronics Engineers (IEEE) 33(11) : 725~743

[confproc] S. Levin / 2017 / Boosting Automatic Commit Classification Into Maintenance Activities By Utilizing Source Code Changes / PROMISE: Proceedings of the 13th International Conference on Predictive Models and Data Analytics in Software Engineering : 97~106

[web] A. Adhikari / 2019 / DocBERT: BERT for Document Classification / arXiv / 10.48550/ARXIV.1904.08398

[web] V. Sanh / 2019 / Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter / arXiv / arXiv:1910.01108

[confproc] M. U. Sarwar / 2020 / Multi-label Classification of Commit Messages using Transfer Learning / 2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW) : 37~42

[journal] 최지훈 / 2022 / Implementation of Git's Commit Message Complex Classification Model for Software Maintenance / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 27(11) : 131~138

[web] / Tiobe / https://www.tiobe.com/tiboe-index,2023

[other] Hultstrand, S. / 2015 / Git-CLI or GUI: Which is most widely used and why?

[other] Miller, C. G. / 2022 / Introduction to Git

[confproc] Devlin, Jacob / 2019 / BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding / Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 1 : 4171~4186

[journal] Chi Sun / 2019 / How to Fine-Tune BERT for Text Classification? / Lecture Notes in Computer Science / Springer International Publishing : 194~206

[confproc] A. Mauczka / 2015 / Dataset of developer-labeled commit messages / 2015 IEEE/ACM 12th Working Conference on Mining Software Repositories / IEEE : 490~493

[confproc] S. Zafar / 2019 / Towards standardizing and improving classification of bug-fix commits / 2019ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) / IEEE : 1~6

[confproc] Li, J. / 2023 / Commit message matters: Investigating impact and evolution of commit message quality / 2023IEEE/ACM 45th International Conference on Software Engineering (ICSE) IEEE : 806~817

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Implementation of Git's Commit Message Classification Model Using GPT-Linked Source Change Data

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Implementation of Git's Commit Message Classification Model Using GPT-Linked Source Change Data

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (21) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.