Assessment of Off-the-Shelf SE-specific Sentiment Analysis Tools: An Extended Replication Study

TL;DR

This study evaluates the effectiveness of software engineering-specific sentiment analysis tools, revealing that off-the-shelf usage can produce contradictory results, and emphasizing the need for platform-specific tuning or retraining.

Contribution

It provides an extended replication and comparison of SE-specific sentiment tools, highlighting their inconsistencies and the importance of customization for accurate analysis.

Findings

Different tools may give contradictory results at a fine-grain level.

Platform-specific tuning improves the agreement with manual annotations.

Off-the-shelf tools may not be reliable without customization.

Abstract

Sentiment analysis methods have become popular for investigating human communication, including discussions related to software projects. Since general-purpose sentiment analysis tools do not fit well with the information exchanged by software developers, new tools, specific for software engineering (SE), have been developed. We investigate to what extent SE-specific tools for sentiment analysis mitigate the threats to conclusion validity of empirical studies in software engineering, highlighted by previous research. First, we replicate two studies addressing the role of sentiment in security discussions on GitHub and in question-writing on Stack Overflow. Then, we extend the previous studies by assessing to what extent the tools agree with each other and with the manual annotation on a gold standard of 600 documents. We find that different SE-specific sentiment analysis tools might lead to contradictory results at a fine-grain level, when used 'off-the-shelf'. Conversely, platform-specific tuning or retraining might be needed to take into account differences in platform conventions, jargon, or document lengths.