Enhancing commit message quality in software capstone projects with generative AI

被引:0
|
作者
Neyem, Andres [1 ,2 ]
Rios-Letelier, Agustin [1 ,2 ]
Cespedes-Arancibia, Kevin [1 ]
Alcocer, Juan Pablo Sandoval [1 ]
Mendoza, Marcelo [1 ,2 ,3 ]
机构
[1] Pontificia Univ Catolica Chile, Dept Comp Sci, Vicuna Mackenna 6840, Santiago, Chile
[2] Natl Ctr Artificial Intelligence CENIA, Vicuna Mackenna 6840, Santiago, Chile
[3] Millennium Inst Fdn Res Data IMFD, Vicuna Mackenna 6840, Santiago, Chile
关键词
Generative AI; Large Language Models; Software engineering education; Capstone courses; Commit message generation;
D O I
10.1016/j.softx.2024.101947
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Software Capstone Projects provide valuable hands-on experience for students in software development, and creating effective commit messages is an essential, though often challenging, part of this process. These messages playa key role in managing repositories, facilitating collaboration, and offering insights into the project's progression for mentors and managers. However, creating high-quality commit messages can be challenging, especially for novice developers. We introduce LetsCommit, a tool designed to improve the traditional Git commit command line interface. The tool utilizes three state-of-the-art Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, to provide commit message suggestions to students. Results from a user experience survey showed high satisfaction, indicating strong potential for incorporating LetsCommit into future projects. Beyond its technical applications, LetsCommit possesses transformative potential in the field of education. The iterative learning process it supports, coupled with real-time insights, reinforces good software development practices and enhances the overall learning experience. These findings highlight LetsCommit's substantial impact on software engineering education, setting the stage for further advancements.
引用
收藏
页数:7
相关论文
共 50 条
  • [21] Commit Quality in Five High Performance Computing Projects
    Agrawal, Kapil
    Amreen, Sadika
    Mockus, Audris
    2015 IEEE/ACM 1ST INTERNATIONAL WORKSHOP ON SOFTWARE ENGINEERING FOR HIGH PERFORMANCE COMPUTING IN SCIENCE (SE4HPCS), 2015, : 24 - 29
  • [22] EdgeGAN: Enhancing Sleep Quality Monitoring in Medical IoT Through Generative AI at the Edge
    Peng K.
    He H.
    Liu J.
    Li T.
    Hou S.
    Qiao S.
    IEEE Internet of Things Magazine, 2024, 7 (03): : 16 - 21
  • [23] Generative AI: Redefining the Future of Software Engineering
    Carleton, Anita
    Falessi, Davide
    Zhang, Hongyu
    Xia, Xin
    IEEE SOFTWARE, 2024, 41 (06) : 34 - 37
  • [24] Utilization of Generative AI for Software and System Development
    Kazuo, Yanoo
    NEC Technical Journal, 2024, 17 (02): : 42 - 45
  • [25] Ipek Ozkaya on Generative AI for Software Architecture
    Raghavan, Priyanka
    IEEE SOFTWARE, 2024, 41 (06) : 141 - 144
  • [26] Generative AI — The End of Systematic Reviews in PhD Projects?
    Zamani, Sanaz
    Sinha, Roopak
    ACM Inroads, 2024, 15 (02) : 48 - 50
  • [27] ENHANCING SENIOR CAPSTONE DESIGN COURSE THROUGH INTERNATIONAL AND MULTIDISCIPLINARY PROJECTS
    Hovsapian, Rob O.
    Shih, Chiang
    Ordonez, Juan
    Vargas, Jose
    Costa, Necesio Gomes
    2012 ASEE ANNUAL CONFERENCE, 2012,
  • [28] Enhancing the Quality and Student Attitude on Capstone Projects Through Activity-Based Learning and Reduced Social Loafing
    Samarakoon, Uthpala
    Manathunga, Kalpani
    Imbulpitiya, Asanthika
    COMPUTER SUPPORTED EDUCATION, CSEDU 2021, 2022, 1624 : 336 - 358
  • [29] Fuzzy analysis and prediction of commit activity in open source software projects
    Saini, Munish
    Kaur, Kuljit
    IET SOFTWARE, 2016, 10 (05) : 136 - 146
  • [30] Streamlined software development in the computer science capstone course 'senior projects'
    Dascalu, S
    INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND CONTROL TECHNOLOGIES, VOL 2, PROCEEDINGS, 2004, : 337 - 342