Can We Use SE-specific Sentiment Analysis Tools in a Cross-Platform Setting?
This addresses the challenge for software engineers in applying sentiment analysis tools reliably across diverse data sources, but it is incremental as it evaluates existing tools rather than introducing new methods.
The paper tackled the problem of using sentiment analysis tools without retraining in cross-platform settings, finding that lexicon-based tools outperform supervised approaches when tested on different data sources, with retraining beneficial only in within-platform scenarios.
In this paper, we address the problem of using sentiment analysis tools 'off-the-shelf,' that is when a gold standard is not available for retraining. We evaluate the performance of four SE-specific tools in a cross-platform setting, i.e., on a test set collected from data sources different from the one used for training. We find that (i) the lexicon-based tools outperform the supervised approaches retrained in a cross-platform setting and (ii) retraining can be beneficial in within-platform settings in the presence of robust gold standard datasets, even using a minimal training set. Based on our empirical findings, we derive guidelines for reliable use of sentiment analysis tools in software engineering.