Matching entities across online social networks

Abstract

Online social networks (OSNs), such as Facebook and Twitter, have become an integral part of our daily lives. There are hundreds of OSNs, and each offers particular services and functionalities. Recent studies show that many OSN users create accounts on multiple OSNs, using the same or different personal information. Collecting all the available data on an individual from several OSNs to fuse into a single profile can provide valuable information. In this paper, we introduce novel machine learning based methods for solving entity resolution (ER), a problem for matching user profiles across multiple OSNs. By using extracted features and supervised learning techniques, we developed classifiers which can perform entity matching between two profiles for the following scenarios: (a) matching users across two OSNs; (b) searching for a user by similar name; and (c) de-anonymizing a user's identity. The constructed classifiers were tested using data collected from two popular OSNs, Facebook and Xing. We then evaluated the classifiers' performances using measures such as true and false positive rates, accuracy, and the area under the receiver operator curve (AUC). The classification performance measured by AUC was quite remarkable, with an AUC of up to 0.982 and an accuracy of up to 95.9% in identifying user profiles across two OSNs.