Research On Mining User’s Social Circle In Social Media

As a media and communication platform, microblog is more and more populararound the world. Users can follow anyone ranges from well-known individuals toreal friends, and read their tweets without their permission. Most users follow alarge number of celebrities and public media in microblog; however, thesecelebrities do not necessarily follow all their fans. Such one-way relationshipabounds in the user network and is displayed in the forms of users’ followees andfollowers, which make it difficult to identify user’s real friends who are containedin the merged list of followees and followers. The aim of this paper is to propose ageneral algorithm for mining users’ real friends in social media and dividing theminto different social circles automatically according to the closeness of theirrelationships. To verify the effectiveness of the proposed algorithm, we build amicroblog application which presents the social circles for users identified by thealgorithm and enable users to modify the proposed results according to her/his realsocial circles. We propose two models for solving this problem, one is Maximizingthe approximate complete SubGraph of the Topology network, another isIncomplete Information Network. With these models, we could divide all friendsinto different circles automatically. We do with this problem by measuring thedistance between them. We demonstrate that our algorithm is superior to traditionalclustering method in terms of F measure and Mean Average Precision. In order tocollecting all the measure data, we designed and developed a Sina Weiboapplication, for each user, they could change the members of any social circle tomatch their real real results.