Analyzing the Correlation Between Toxic Comments and Code Quality

Jaime Sayago-Heredia; Gustavo Chango Sailema; Ricardo Pérez-Castillo; Mario Piattini

doi:10.1002/smr.2739

Analyzing the Correlation Between Toxic Comments and Code Quality

Jaime Sayago-Heredia^*
, Gustavo Chango Sailema
, Ricardo Pérez-Castillo
, Mario Piattini

^*Corresponding author for this work

PUCE Esmeraldas

Research output: Contribution to journal › Article › peer-review

Abstract

Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.

Original language	English
Journal	Journal of software: Evolution and Process
DOIs	https://doi.org/10.1002/smr.2739
State	Published - 12 Nov 2024

Bibliographical note

Publisher Copyright:
© 2024 The Author(s). Journal of Software: Evolution and Process published by John Wiley & Sons Ltd.

Funding

This research was supported by MCIN/AEI (PID2022\u2010137944NB\u2010I00 and PDC2022\u2010133051\u2010I00) and the European Union NextGenerationEU/PRTR; additional financial support was provided by the UCLM Own Research Plan and co\u2010financed at 85% by the European Regional Development Fund (FEDER UNION) (2022\u2010GRIN\u201034110). Funding: P\u00E9rez and Piattini thank the PID2022\u2010137944NB\u2010I00 (SMOOTH Project) and PDC2022\u2010133051\u2010I00 (QU\u2010ASAP Project), funded by MCIN/AEI and by the European Union NextGenerationEU/PRTR, as well as financial support for the execution of applied research projects within the framework of the UCLM Own Research Plan, co\u2010financed at 85% by the European Regional Development Fund (FEDER) UNION (2022\u2010GRIN\u201034110).

Funders	Funder number
FEDER UNION
Ministerio de Ciencia e Innovación
PRTR
European Union NextGenerationEU
Universidad de Castilla-La Mancha
Agencia Estatal de Investigación	PDC2022‐133051‐I00, PID2022‐137944NB‐I00
European Regional Development Fund	2022‐GRIN‐34110

Keywords

commit analysis
GitHub
sentiments analysis
software engineering
software quality
SonarQube
toxic comment classification

Access to Document

10.1002/smr.2739

Cite this

@article{35e95835c7cc4f5ab289e018485068b0,

title = "Analyzing the Correlation Between Toxic Comments and Code Quality",

abstract = "Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.",

keywords = "commit analysis, GitHub, sentiments analysis, software engineering, software quality, SonarQube, toxic comment classification",

author = "Jaime Sayago-Heredia and Gustavo Chango Sailema and Ricardo P{\'e}rez-Castillo and Mario Piattini",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s). Journal of Software: Evolution and Process published by John Wiley \& Sons Ltd.",

year = "2024",

month = nov,

day = "12",

doi = "10.1002/smr.2739",

language = "English",

journal = "Journal of software: Evolution and Process",

issn = "1532-060X",

publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Analyzing the Correlation Between Toxic Comments and Code Quality

AU - Sayago-Heredia, Jaime

AU - Sailema, Gustavo Chango

AU - Pérez-Castillo, Ricardo

AU - Piattini, Mario

PY - 2024/11/12

Y1 - 2024/11/12

N2 - Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.

AB - Software development has a relevant human side, and this could, for example, imply that developers' feelings have an impact on certain aspects of software development such as quality, productivity, or performance. This paper explores the effects of toxic emotions on code quality and presents the SentiQ tool, which gathers and analyzes sentiments from commit messages (obtained from GitHub) and code quality measures (obtained from SonarQube). The SentiQ tool we proposed performs a sentiment analysis (based on natural language processing techniques) and relates the results to the code quality measures. The datasets extracted are then used as the basis on which to conduct a preliminary case study, which demonstrates that there is a relationship between toxic comments and code quality that may affect the quality of the whole software project. This has resulted in the drafting of a predictive model to validate the correlation of the impact of toxic comments on code quality. The main implication of this work is that these results could, in the future, make it possible to estimate code quality as a function of developers' toxic comments.

KW - commit analysis

KW - GitHub

KW - sentiments analysis

KW - software engineering

KW - software quality

KW - SonarQube

KW - toxic comment classification

UR - https://www.scopus.com/pages/publications/85208794089

U2 - 10.1002/smr.2739

DO - 10.1002/smr.2739

M3 - Article

SN - 1532-060X

JO - Journal of software: Evolution and Process

JF - Journal of software: Evolution and Process

ER -

Analyzing the Correlation Between Toxic Comments and Code Quality

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Cite this