Assessment of Off-the-Shelf SE-specific Sentiment Analysis Tools: An Extended Replication Study
This work addresses the problem of unreliable sentiment analysis in software engineering empirical studies, which can threaten conclusion validity, but it is incremental as it builds on and extends previous replication studies.
The study assessed the reliability of off-the-shelf software engineering-specific sentiment analysis tools by replicating and extending prior research, finding that these tools can produce contradictory results at a fine-grain level on a gold standard of 600 documents, indicating a need for platform-specific tuning.
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.