Understanding Emotions of Developer Community Towards Software Documentation

TL;DR

This paper analyzes developer sentiments towards software documentation by examining commit messages from nearly 1,000 GitHub projects, revealing that a significant portion express trust, which can inform better documentation practices.

Contribution

It introduces a sentiment analysis approach to understand developer perceptions of documentation through commit messages, a novel step in improving software documentation quality.

Findings

45% of documentation-related commits express trust.

Sentiment analysis reveals emotional perceptions towards documentation.

Insights can guide training and improvements in documentation practices.

Abstract

The availability of open-source projects facilitates developers to contribute and collaborate on a wide range of projects. As a result, the developer community contributing to such open-source projects is also increasing. Many of the projects involve frequent updates and extensive reuses. A well-updated documentation helps in a better understanding of the software project and also facilitates efficient contribution and reuse. Though software documentation plays an important role in the development and maintenance of software, it also suffers from various issues that include insufficiency, inconsistency, ill-maintainability, and so on. Exploring the perception of developers towards documentation could help in understanding the reasons behind prevalent issues in software documentation. It could further aid in deciding on training that could be given to the developer community towards building more sustainable projects for society. Analyzing sentiments of contributors to a project could provide insights on understanding developer perceptions. Hence, as the first step towards this direction, we analyze sentiments of commit messages specific to the documentation of a software project. To this end, we considered the commit history of 998 GitHub projects from the GHTorrent dataset and identified 10,996 commits that correspond to the documentation of repositories. Further, we apply sentiment analysis techniques to obtain insights on the type of sentiment being expressed in commit messages of the selected commits. We observe that around 45% of the identified commit messages express trust emotion.