User Identification across Social Networks using the Web Profile and Friend Network

Today, it is common that people are users of more than one social network and their friends may also be registered on multiple websites. A facility to aggregate our online friends into a single integrated environment would enable us to keep up-to-date with our virtual contacts more easily, as well as to provide improved facility to search for users across different websites. In this paper, we propose a method to identify users based on web profile matching and further extend its effectiveness by incorporating the user’s friend network. We collect and study real-life data from two popular social networks and evaluate the importance of profile information. Machine learning algorithms are used in our experiments and we present results of pure profile-based user identification and demonstrate the benefits of incorporating the friend network in the classification process. We show that our combined method successfully identifies up to 93% of duplicated users across social networking websites.