Abstract: In the recent trend, there are plenty of apps dominating social networks. There are several mobile apps and social site based apps are malicious and duplicate in features. Facing the large amount of apps, app retrieval and app recommendation become imperative task, while users can easily use them to acquire their desired apps without malicious and duplicate. To classify different apps based on its features and security levels is the major task of the proposed work. The recent methods are conducted mostly relying on user’s log or app’s details, which can only detect whether two apps are downloaded or used by the user. Moreover, apps contain many general relationships other than similarity, such as one app needs many permissions, the proposed work classifies the app based on the permission asked by the app. These relationships cannot be performed without the whole details of app descriptions. Reviews contain user’s viewpoint and judgment to apps, thus they can be used to calculate relationship between apps. To use reviews, this paper proposes a similarity and rule matching process by combining review similarity and app rule verification.

Keywords: Data Mining, Mobile APP, Relations among complexity measures, similarity measures, text processing, web mining, malicious detection.