Abstract

Mobile application development has now been in the mainstream and a lot of mobile applications have been released to Apple App Store and GooglePlay Store. As there are many applications in the same category and the competition is very high in the market, mobile development teams need to get user feedback on their applications so that they can improve quality of the applications. An important source of feedback is user review on App Store and Play Store from which the developers can analyze problems and recommendations for future maintenance and evolution of the applications. Since there might be a large number of user reviews for each release of a mobile application, this paper proposes an automated approach to classifying user reviews as bug reports or feature requests. These classification results are used as a basis for generating tickets for an issue tracking system, i.e. Jira. In user review classification, text classification, natural language processing, sentiment analysis, and review metadata are used with several machine learning algorithms, i.e. Naive Bayes, Decision Tree, KNN, LinearSVC, Logistic Regression, and Ensemble methods. The best classifiers for both categories of reviews are used further in an implementation of a Jira ticket generating tool. The tool considers semantic similarity of review comments and can filter out duplicate user reviews. When necessary, the tool applies text summarization to the user review to extract the title of a ticket for the corresponding bug report or feature request. The approach can facilitate the mobile development team in their maintenance task as the developers can pick the tickets and work on them to improve the application in a future release.

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.