Developer Sentiment in Open Source: Effects of Commit Frequency, Time, and Issue Characteristics

View at publisher Summarise with VIRAT
Authors: Mahmudur Rahman, Mohammad Kawsar Ahamed Siam, Moudud Hassan, Shohel Ahmed
Cited by: 0
References: 26

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Developer emotions in open-source projects strongly influence productivity, code quality, creativity, and team dynamics. Sentiment analysis of commit messages provides insights into these emotional states and their impact on project outcomes. In this study, we analyzed 630,164 commit messages from the 20 MAD dataset using a fine-tuned seBERT model. Contributors were grouped by commit frequency to examine how sentiment varies with activity levels. We also studied correlations with commit time, issue type (bug vs. non-bug), and priority. Our findings show that low and medium-frequency contributors express more negative sentiment. Commits made in the afternoon are generally more negative than morning or late-night commits. High-priority bug-related tasks trigger stronger negative emotions. We validated our findings using multiple parametric tests for statistical significance. Our findings can help project managers intervene early with support, adjust schedules, manage workloads, and provide emotional guidance during stressful periods.

Fields of Study & Subjects

Software Engineering Research Software Engineering Techniques and Practices Open Source Software Innovations

Publication details

Journal / source
International Conference on Advanced Research in Computing (ICARC)
Pages
1–6
Publication date
18 February 2026
Language
EN