Toward an Opinion Mining System in Software Engineering

Abstract

Discussions of experienced software engineers in various social forums (e.g., Stack Overflow) become valuable information for other software engineers to perform software development activities. These discussions centered around software-specific entities (e.g., tools, libraries, and APIs) where software engineers provide their opinions on the various aspects (e.g., bug, performance, and security) of the entities. Such opinions are often embedded with sentiments (i.e., positive or negative) that play crucial roles to a considerable degree in the perceptions of other software engineers about those entities. That perceptions influence the decisions they make about whether and how they should use those entities for software development. However, given the plethora of information posted in unstructured formats in technical social forums, it is a challenging task for a software engineer to mine the opinions manually and make informed decisions about those entities. Here, we envision an automated software system that will mine the technical discussions from the unstructured content of social forums and generate opinions on the various aspects of the entities.