期刊名称：International Journal of Future Generation Communication and Networking
印刷版ISSN：2233-7857
出版年度：2016
卷号：9
期号：1
页码：35-46
DOI：10.14257/ijfgcn.2016.9.1.04
出版社：SERSC
摘要：Aiming at the division roughness of topic classification existing in the most online social networks community, the improved particle swarm optimization algorithm is applied to refine community topics and concepts of community seeds and community topic are also introduced. In this paper, first of all, the explicit links existing in the community are mined, and the basic community structure is constructed, then the community content is deeply analyzed, according to implicit feature between nodes under online community, community topic categories are elaborately refined until structure is stable. Experiments show that this proposed algorithm can accelerate the convergence of the node and greatly improves the topic mining accuracy of online social network compared with the state-of- art CR2NDAS model and PLSA model.
关键词：Improved particle swarm optimization algorithm; online social network; ; Community topic; Community seed; Topic refinement
