基于超网络的舆论领袖识别应用研究

Recognition of Online Opinion Leaders Based on Supernetwork Analysis

舆论领袖对网络舆论的形成具有重要推动作用,可以影响网络舆论的走向,因此识别网络舆论领袖对于及时掌握舆情、引导舆论有重要意义。本研究将超网络分析法应用到网络舆论领袖的识别中,首先在对网络舆论构成及关系进行分析的基础上,建立社交子网、话题子网、观点子网等子网络,并根据三者间的关联关系将它们集成为一个完整的网络舆论超网络模型;在此基础上,提出可用以识别网络舆论领袖的超网络测度指标,包括节点超度、超边重叠度、集聚系数、平均最短距离等;最后通过"钱云会"事件的实例分析证明了该方法的可行性,具有很强的实际应用价值和理论指导意义。

Opinion leaders on the internet play an important role in promoting the formation of online public opinion, which can influence the direction of public opinion. In this paper, we use supemetwork analysis to recognize the opinion leaders of on- line communities. First, we set up the social network, the topic network and the keyword network according to the components and relationships of online public opinion, and built the supernetwork model. Then, we proposed some attribute indexes of su- pernetwork which can be used to recognize the opinion leaders, such as clustering coefficient, vertex hyperdegree, hyperedge density, vertex-vertex distance. Finally, we used a case study to demonstrate the theoretical significance and practical value of this method.