Alias Detection Across Multi-online Applications Based on User's Behavior Characteristics

Abstract

The quickly development of many online applications benefit our daily life. But on the other hand, user usually holds several aliases in different online applications. The aliases across multi-online applications detection are becoming more and more important for E-marketing and user's behavior monitoring. In this paper, we propose a method for detecting aliases across multi-online applications. Firstly, we employ the active and positive methods to collect the user's alias and behavior information from several famous applications, including Email, RenRen and etc. Then we analyzed the user's behavior characteristics in specific applications, and some interesting findings are proposed. Finally, we perform the alias detection based on user's behavior profiles, including the similarity of the ID and the number of appearance in specific IP address. According to user's behavior habit, the aliases belong to the same physical users are usually similar with each other. Furthermore, one specific user usually use the same computer to login into different applications, thus the IP addresses used for accessing those applications usually same with each other. Based on those assumptions we employ the Bayesian Network to perform alias detection. Empirical results based on actual data verify the efficiency and correctness of the proposed methods.