Linking social network accounts by modeling user spatiotemporal habits

Abstract

Identifying the physical person behind an SNS account has become a critical issue in investigations of SNS-involved crime cases. It is a challenging task because information provided by users on an SNS platform could be false, conflicting, missing and deceptive. One way to gain an accurate profile of a user is to link up all their multiple accounts created on different social platforms, which is referred to as Account Linkage (AL). However, existing AL techniques suffer from the problem of information unreliability. Recent advances in location acquisition and wireless communication technologies give rise to new opportunities for AL. In this paper, we propose a framework that links up multiple accounts belonging to the same individual by comparing habit patterns extracted from user-generated location data. We built a topic model to capture users habit patterns in both spatial and temporal dimensions. Results of experiments carried out on a real-world dataset demonstrate the feasibility and validity of the proposed framework.