Micro-blog User Community Detection by Focusing on Micro-blog Content and Community Structure

Micro-blog community detection is one of the hot problems of Micro-blog platform. There are many existing community detection methods that are dedicated to detect community by only considering the topological structure. To detect Micro-blog community better, we considering the Micro-blog content as well as the topological structure. In Micro-blog community, the essence of a concept is semantic objects in the real world. The concept is composed of the object's attribute set, and the attribute set is a set of nouns that essentially can represent the object. In this article, we let user be object and calculate the interest similarity by the object's attribute set. First, we establish a micro-blog social network by analyzing the object's attribute set. Second, we find the clustering directions for each object by the Random Walk method. Then, we detect micro-blog user community following the clustering directions. Finally, experiments performed to verify the efficiency of our method from the two aspects of community structure and interest cohesion.