Disparity between the Programmatic Views and the User Perceptions of Mobile Apps

Abstract

User perception in any mobile-app ecosystem, is represented as user ratings of apps. Unfortunately, the user ratings are often biased and do not reflect the actual usability of an app. To address the challenges associated with selection and ranking of apps, we need to use a comprehensive and holistic view about the behavior of an app. In this paper, we present and evaluate Trust based Rating and Ranking (TRR) approach. It relies solely on an apps' internal view that uses programmatic artifacts. We compute a trust tuple (Belief, Disbelief, Uncertainty - B, D, U) for each app based on the internal view and use it to rank the order apps offering similar functionality. Apps used for empirically evaluating the TRR approach are collected from the Google Play Store. Our experiments compare the TRR ranking with the user review-based ranking present in the Google Play Store. Although, there are disparities between the two rankings, a slightly deeper investigation indicates an underlying similarity between the two alternatives.