Bug report, feature request, or simply praise? On automatically classifying app reviews

摘要

App stores like Google Play and Apple AppStore have over 3 Million apps covering nearly every kind of software and service. Billions of users regularly download, use, and review these apps. Recent studies have shown that reviews written by the users represent a rich source of information for the app vendors and the developers, as they include information about bugs, ideas for new features, or documentation of released features. This paper introduces several probabilistic techniques to classify app reviews into four types: bug reports, feature requests, user experiences, and ratings. For this we use review metadata such as the star rating and the tense, as well as, text classification, natural language processing, and sentiment analysis techniques. We conducted a series of experiments to compare the accuracy of the techniques and compared them with simple string matching. We found that metadata alone results in a poor classification accuracy. When combined with natural language processing, the classification precision got between 70-95% while the recall between 80-90%. Multiple binary classifiers outperformed single multiclass classifiers. Our results impact the design of review analytics tools which help app vendors, developers, and users to deal with the large amount of reviews, filter critical reviews, and assign them to the appropriate stakeholders.