In this paper, we examine the emerging copycat issue in the mobile apps market. Using a combination of machine learning techniques such as natural language processing, latent sematic analysis, network-based clustering and image analysis, we are able to detect two types of copycats (deceptive and non-deceptive) at a large scale. Based on our detected copycats, we conduct econometric analysis to understand the major impacts on the download of original apps. Our final results suggest that the copycat apps can be either friends or foes of the original apps.
Session 2B: Mobile Technologies, Presentation 1, Conference submission 93