A Cognitive Agent for Mining Bugs Reports, Feature Suggestions and Sentiment in a Mobile Application Store

Sergio Muñoz López, Antonio Fernández, Oscar Araque & Carlos A. Iglesias (2018). A Cognitive Agent for Mining Bugs Reports, Feature Suggestions and Sentiment in a Mobile Application Store. In Proceedings of The 4th International Conference on Big Data Innovations and Applications (Innovate-Data 2018).

Abstract:
Over the last years, mobile applications and their corresponding distribution platforms have gained momentum. Applications stores allow users to write reviews and ratings about the apps, giving feedback to developers. User ratings and reviews may help to improve software quality, solve bugs and develop new features. However, this data is hard to be handled by an individual due to the ever growing amount of textual reviews. This paper proposes the use of cognitive computing technologies for addressing this challenge, by developing a smart agent able to mine bugs reports, feature suggestions and sentiment expressed in mobile app reviews. The main contributions of this paper are: the design of a cognitive agent for assisting developers in managing their interaction with their users, the application of machine learning algorithms for bug and feature request detection, and the agent implementation in a real scenario.