关键词: 社会网络分析, 网络社区, 主题周期划分

Abstract: Current research on topic development analysis mainly focuses on finding general trend， thus it can not be used to answer the question like “What state is the topic being at?”. This paper presents a new task which aims to segment the development of a scientific topic into several states. Based on community partitioning in social network， a core group technique is proposed. According to the division phase and interphase in the life cycle of core groups， the development of a topic is separated into four states， i.e. birth state， extending state， saturation state and shrinkage state. Experimental results on a real dataset show that the proposed core group method can accurately judge the generation of a new topic， and the growth pattern of a core group greatly influences the development of its relevant topic.

Key words: social network analysis, network community, topic cycle partitioning