Trust evaluation in virtual software development teams using BERT-based language models

Nowadays, people from different geographical areas can be closely related thanks to advances in information and communication technologies. This has a greater impact in software development organizations where their members form virtual work teams. In these new co-located work scenarios, the constru...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Zapata, Sergio G., Gallardo, Facundo, Sevilla, Gustavo A., Torres, Estela, Forradellas Martinez, Raymundo Quilez
Formato: Articulo
Lenguaje:Inglés
Publicado: 2023
Materias:
Ciencias Informáticas
BERT-based language model
Social software engineering
Trust analysis
Modelo de lenguaje BERT
Ingeniería de software social
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/151317
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-151317
record_format dspace
spelling I19-R120-10915-1513172023-04-12T20:03:13Z http://sedici.unlp.edu.ar/handle/10915/151317 issn:1666-6038 Trust evaluation in virtual software development teams using BERT-based language models Evaluación de confianza en equipos virtuales de desarrollo de software usando modelos de lenguajes basados en BERT Zapata, Sergio G. Gallardo, Facundo Sevilla, Gustavo A. Torres, Estela Forradellas Martinez, Raymundo Quilez 2023-04 2023-04-12T12:54:58Z en Ciencias Informáticas BERT-based language model Social software engineering Trust analysis Modelo de lenguaje BERT Ingeniería de software social Modelo de lenguaje BERT Nowadays, people from different geographical areas can be closely related thanks to advances in information and communication technologies. This has a greater impact in software development organizations where their members form virtual work teams. In these new co-located work scenarios, the construction of interpersonal trust is more complex and its impact is very relevant in the performance of software development teams. This paper presents the results of the performance evaluation of four pre-trained language models based on BERT applied to trust analysis tasks. For this work, a small dataset of 1453 comments obtained from software projects stored on Github was created. The evaluated language models achieved moderately good values, in the order of 0.84 for the F1-score metric, which augurs that with further research they could be significantly improved. Actualmente personas de distintas zonas geográficas pueden estar fuertemente relacionadas gracias a los avances en las tecnologías de información y comunicación. Esto tiene un impacto mayor en organizaciones de desarrollo de software en donde sus miembros conforman equipos virtuales de trabajo. En estos nuevos escenarios colocalizados de trabajo la construcción de confianza interpersonal es más compleja y su impacto es muy relevante en el desempeño de los equipos de desarrollo de software. Este trabajo presenta los resultados de la evaluación de desempeño de cuatro modelos de lenguaje pre-entrenados basados en BERT aplicados a tareas de análisis de trust. Para este trabajo se creó un pequeño dataset de 1453 comentarios obtenidos de proyectos de software almacenados en Github. Los modelos de lenguaje evaluados alcanzaron valores moderadamente buenos, del orden de 0.84 para la métrica F1-score, lo que augura que con una mayor investigación podrían mejorarse significativamente. Facultad de Informática Articulo Articulo http://creativecommons.org/licenses/by-nc/4.0/ Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
BERT-based language model
Social software engineering
Trust analysis
Modelo de lenguaje BERT
Ingeniería de software social
Modelo de lenguaje BERT
spellingShingle Ciencias Informáticas
BERT-based language model
Social software engineering
Trust analysis
Modelo de lenguaje BERT
Ingeniería de software social
Modelo de lenguaje BERT
Zapata, Sergio G.
Gallardo, Facundo
Sevilla, Gustavo A.
Torres, Estela
Forradellas Martinez, Raymundo Quilez
Trust evaluation in virtual software development teams using BERT-based language models
topic_facet Ciencias Informáticas
BERT-based language model
Social software engineering
Trust analysis
Modelo de lenguaje BERT
Ingeniería de software social
Modelo de lenguaje BERT
description Nowadays, people from different geographical areas can be closely related thanks to advances in information and communication technologies. This has a greater impact in software development organizations where their members form virtual work teams. In these new co-located work scenarios, the construction of interpersonal trust is more complex and its impact is very relevant in the performance of software development teams. This paper presents the results of the performance evaluation of four pre-trained language models based on BERT applied to trust analysis tasks. For this work, a small dataset of 1453 comments obtained from software projects stored on Github was created. The evaluated language models achieved moderately good values, in the order of 0.84 for the F1-score metric, which augurs that with further research they could be significantly improved.
format Articulo
Articulo
author Zapata, Sergio G.
Gallardo, Facundo
Sevilla, Gustavo A.
Torres, Estela
Forradellas Martinez, Raymundo Quilez
author_facet Zapata, Sergio G.
Gallardo, Facundo
Sevilla, Gustavo A.
Torres, Estela
Forradellas Martinez, Raymundo Quilez
author_sort Zapata, Sergio G.
title Trust evaluation in virtual software development teams using BERT-based language models
title_short Trust evaluation in virtual software development teams using BERT-based language models
title_full Trust evaluation in virtual software development teams using BERT-based language models
title_fullStr Trust evaluation in virtual software development teams using BERT-based language models
title_full_unstemmed Trust evaluation in virtual software development teams using BERT-based language models
title_sort trust evaluation in virtual software development teams using bert-based language models
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/151317
work_keys_str_mv AT zapatasergiog trustevaluationinvirtualsoftwaredevelopmentteamsusingbertbasedlanguagemodels
AT gallardofacundo trustevaluationinvirtualsoftwaredevelopmentteamsusingbertbasedlanguagemodels
AT sevillagustavoa trustevaluationinvirtualsoftwaredevelopmentteamsusingbertbasedlanguagemodels
AT torresestela trustevaluationinvirtualsoftwaredevelopmentteamsusingbertbasedlanguagemodels
AT forradellasmartinezraymundoquilez trustevaluationinvirtualsoftwaredevelopmentteamsusingbertbasedlanguagemodels
AT zapatasergiog evaluaciondeconfianzaenequiposvirtualesdedesarrollodesoftwareusandomodelosdelenguajesbasadosenbert
AT gallardofacundo evaluaciondeconfianzaenequiposvirtualesdedesarrollodesoftwareusandomodelosdelenguajesbasadosenbert
AT sevillagustavoa evaluaciondeconfianzaenequiposvirtualesdedesarrollodesoftwareusandomodelosdelenguajesbasadosenbert
AT torresestela evaluaciondeconfianzaenequiposvirtualesdedesarrollodesoftwareusandomodelosdelenguajesbasadosenbert
AT forradellasmartinezraymundoquilez evaluaciondeconfianzaenequiposvirtualesdedesarrollodesoftwareusandomodelosdelenguajesbasadosenbert
_version_ 1765659943852048384

Ejemplares similares