A Holistic Ranking Scheme for Apps

Abstract

App stores or application distribution platforms allow users to present their sentiments about apps in the forms of ratings and reviews. However, selecting the “best one” from available apps that offer similar functionality is difficult task - especially, if the selection process only uses the average star rating of the apps. To address this challenge, we have introduced a trust-based selection and ranking system of similar apps by combining the programmatic view (“internal view”) and the sentiments based on users reviews (“external view”). The rankings based on the average star ratings are compared with the rankings generated by our approach. We empirically evaluate our approach by using the publically available apps from the Google Play Store. For this study, we have chosen a dataset of 250 apps with total 114,480 reviews from top 5 different categories - of which we focused our experiments on 90 apps that have at least 1000 reviews. Our experiments indicate that proposed holistic ranking that encompasses both the internal and external views is a better alternative than any ranking that focuses only on the internal or external view.