Affiliations: Graduate School of Information Science and Technology, Osaka University, Suita, Japan
Correspondence:
[*]
Corresponding author: Shuaicai Ren, Graduate School of Information Science and Technology, Osaka University, Suita, Japan. E-mail: [email protected].
Abstract: User review is a crucial component of open mobile app market, such as the Google Play Store. These markets allow users to submit reviews for downloaded apps. By analyzing these reviews, app developers can find new or missing features. However, owing to the huge number of reviews, this manual process is time-consuming and unscalable. An automatic method for user review clustering and goal-model identification has been proposed. However, this method limits the numbers of sub-goals in the goal model. To address this, we propose a comprehensive user review clustering method. This method comprises two components. One is a latent Dirichlet allocation (LDA) model, which clusters user reviews into several topics. The other is a distance-based clustering algorithm, which is an improved version of the existing clustering method.
Keywords: Goal modeling, clustering, user reviews, topic models
