Sentiment Polarity Detection for Software Development
The role of sentiment analysis is increasingly emerging to study software developers’ emotions by mining crowd-generated content within social software engineering tools. However, off-the-shelf sentiment analysis tools have been trained on non-technical domains and general-purpose social media, thus resulting in misclassifications of technical jargon and problem reports. Here, we present Senti4SD, a classifier specifically trained to support sentiment analysis in developers’ communication channels. Senti4SD is trained and validated using a gold standard of Stack Overflow questions, answers, and comments manually annotated for sentiment polarity. It exploits a suite of both lexicon- and keyword-based features, as well as semantic features based on word embedding. With respect to a mainstream off-the-shelf tool, which we use as a baseline, Senti4SD reduces the misclassifications of neutral and positive posts as emotionally negative. To encourage replications, we release a lab package including the classifier, the word embedding space, and the gold standard with annotation guidelines.
Wed 30 May Times are displayed in time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
11:00 - 12:30: Human and Social Aspects of Computing ITechnical Papers / Journal first papers at J1 room Chair(s): Ita RichardsonLero - The Irish Software Research Centre and University of Limerick | |||
11:00 - 11:20 Talk | Sentiment Analysis for Software Engineering: How Far Can We Go? Technical Papers Bin Lin, Fiorella ZampettiUniversity of Sannio, Gabriele BavotaUniversità della Svizzera italiana (USI), Massimiliano Di PentaUniversity of Sannio, Michele LanzaUniversità della Svizzera italiana (USI), Rocco OlivetoUniversity of Molise | ||
11:20 - 11:40 Talk | Identifying Features in Forks Technical Papers Shurui ZhouCarnegie Mellon University, USA, Ştefan Stănciulescu, Olaf Leßenich, Yingfei XiongPeking University, Andrzej WąsowskiIT University of Copenhagen, Denmark, Christian K{\"a}stnerCarnegie Mellon University Pre-print File Attached | ||
11:40 - 12:00 Talk | Roles and Impacts of Hands-on Software Architects in Five Industrial Case Studies Technical Papers Inayat Rehman, Mehdi MirakhorliRochester Institute of Technology, Mei NagappanUniversity of Waterloo, Azad Aralbay, Matthew Thornton | ||
12:00 - 12:20 Talk | Sentiment Polarity Detection for Software Development Journal first papers Fabio CalefatoUniversity of Bari, Filippo LanubileUniversity of Bari, Federico Maiorano, Nicole NovielliUniversity of Bari DOI Pre-print | ||
12:20 - 12:30 Talk | Q&A in groups Technical Papers |