Colección SciELO Chile

Departamento Gestión de Conocimiento, Monitoreo y Prospección
Consultas o comentarios: productividad@anid.cl
Búsqueda Publicación
Búsqueda por Tema Título, Abstract y Keywords



Enhancing commit message quality in software capstone projects with generative AI
Indexado
WoS WOS:001354477900001
Scopus SCOPUS_ID:85208118451
DOI 10.1016/J.SOFTX.2024.101947
Año 2024
Tipo artículo de investigación

Citas Totales

Autores Afiliación Chile

Instituciones Chile

% Participación
Internacional

Autores
Afiliación Extranjera

Instituciones
Extranjeras


Abstract



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.

Revista



Revista ISSN
Software X 2352-7110

Métricas Externas



PlumX Altmetric Dimensions

Muestra métricas de impacto externas asociadas a la publicación. Para mayor detalle:

Disciplinas de Investigación



WOS
Computer Science, Software Engineering
Scopus
Computer Science Applications
Software
SciELO
Sin Disciplinas

Muestra la distribución de disciplinas para esta publicación.

Publicaciones WoS (Ediciones: ISSHP, ISTP, AHCI, SSCI, SCI), Scopus, SciELO Chile.

Colaboración Institucional



Muestra la distribución de colaboración, tanto nacional como extranjera, generada en esta publicación.


Autores - Afiliación



Ord. Autor Género Institución - País
1 Neyem, Andres - Pontificia Universidad Católica de Chile - Chile
Centro Nacional de Inteligencia Artificial (CENIA) - Chile
Centro Nacional de Inteligencia Artificial - Chile
2 Rios-Letelier, Agustin - Pontificia Universidad Católica de Chile - Chile
Centro Nacional de Inteligencia Artificial (CENIA) - Chile
Centro Nacional de Inteligencia Artificial - Chile
3 Cespedes-Arancibia, Kevin - Pontificia Universidad Católica de Chile - Chile
4 Alcocer, Juan Pablo Sandoval - Pontificia Universidad Católica de Chile - Chile
5 MENDOZA-ROCHA, MARCELO GABRIEL Hombre Pontificia Universidad Católica de Chile - Chile
Centro Nacional de Inteligencia Artificial (CENIA) - Chile
Instituto Milenio Fundamentos de los Datos - Chile
Centro Nacional de Inteligencia Artificial - Chile

Muestra la afiliación y género (detectado) para los co-autores de la publicación.

Financiamiento



Fuente
Chilean National Agency for Research and Development ANID
CENIA
National Center for Artificial Intelligence
National Center for Artificial Intelligence (CENIA)
Chilean National Agency for Research and Development ANID)/Scholarship Program

Muestra la fuente de financiamiento declarada en la publicación.

Agradecimientos



Agradecimiento
Andres Neyem, Agustin Rios-Letelier and Marcelo Mendoza are supported by the National Center for Artificial Intelligence (CENIA FB210017, Basal ANID). Kevin Cespedes-Arancibia is supported by the Chilean National Agency for Research and Development ANID)/Scholarship Program/DOCTORADO NACIONAL/2024-21241430. Finally, the authors would like to thank all the students from the IIC2154 capstone course who were involved in this educational research project.
Andres Neyem, Agustin Rios-Letelier and Marcelo Mendoza are supported by the National Center for Artificial Intelligence (CENIA FB210017, Basal ANID). Kevin C\u00E9spedes-Arancibia is supported by the Chilean National Agency for Research and Development ANID)/Scholarship Program/DOCTORADO NACIONAL/ 2024-21241430 . Finally, the authors would like to thank all the students from the IIC2154 capstone course who were involved in this educational research project.

Muestra la fuente de financiamiento declarada en la publicación.