论文部分内容阅读
现有的微博社交网络社区挖掘方法多是基于网络结构进行,忽略了节点本身行为的重要性,并且不能同时实现对大规模复杂网络结构适应性和社区挖掘的高效性。为缓解上述问题,提出了一种基于网络距离和内容相似度的微博社交网络社区划分方法,该方法在考虑微博社交网络结构的同时兼顾了网络中节点的历史微博内容,通过对历史微博数据的分析提高社区划分的精确度。文中对Louvain算法和其模块性的修改使用,保证了该方法能够处理大规模网络数据,同时又能保证社区挖掘的效率。实验证明,该方法能够高效地挖掘微博网络社区结构,对学术研究和商业应用都有十分重要的意义。
The existing methods for mining social networks in Weibo mainly rely on the network structure, ignoring the importance of the node’s own behavior and failing to achieve both the adaptability to large-scale and complex network structures and the efficiency of community mining. In order to alleviate the above problems, this paper proposes a method of social network of microblogging based on network distance and content similarity. This method not only considers the structure of microblog’s social network, but also takes into account the historical content of microblogs. Analysis of Weibo data improves the accuracy of community segmentation. In this paper, the Louvain algorithm and its modular modification are used to ensure that the method can process large-scale network data while ensuring the efficiency of community mining. The experiment proves that this method can effectively excavate the Weibo network community structure, which is of great significance to academic research and commercial application.