Back to overview

Two Datasets for Sentiment Analysis in Software Engineering

Type of publication Peer-reviewed
Publikationsform Proceedings (peer-reviewed)
Author Lin Bin, Zampetti Fiorella, Oliveto Rocco, Penta Massimiliano Di, Lanza Michele, Bavota Gabriele,
Project PROBE - Live Actionable Software Analytics
Show all

Proceedings (peer-reviewed)

Page(s) 712 - 712
Title of proceedings Proceedings of ICSME 2018 (26th International Conference on Software Analysis, Evolution, and Reengineering)

Open Access

Type of Open Access Repository (Green Open Access)


Software engineering researchers have used senti- ment analysis for various purposes, such as analyzing app reviews and detecting developers’ emotions. However, most existing sentiment analysis tools do not achieve satisfactory performance when used in software-related contexts, and there are not many ready-to-use datasets in this domain. To facilitate the creation of better tools and sufficient validation of sentiment analysis techniques, we present two datasets with labeled sentiments, which are extracted from mobile app reviews and Stack Overflow discussions, respectively. The web app we created to support the labeling of the Stack Overflow dataset is also provided.