Detecting Community Kernels in Large Social Networks

摘要: In many social networks, there exist two types of users that exhibit different influence and behavior. For instance, statistics have shown less than 1% the Twitter (e.g. entertainers, politicians, writers) produce 50% its content, while others fans, followers, readers) much completely this paper, we define explore a novel problem called community kernel detection in order to uncover hidden structure large networks. We discover influential pay closer attention those who are more similar them, which leads natural partition into kernels. propose Greedy BA, efficient algorithms for finding kernels is based on maximum cardinality search, BA formalizes an optimization framework. conduct experiments three networks: Twitter, Wikipedia, Coauthor, show achieves average 15%-50% performance improvement over other state-of-the-art algorithms, 6-2,000 times faster detecting