基于社会网络增量的动态社区组织探测

在现实世界中，社会网络结构并不是一成不变的，而是随着时间的推移不断变化，同样社区作为社会网络的一个本质特性也是如此。为了揭示真实的网络社区结构，该文提出一种基于属性加权网络的增量式动态社区发现算法，将网络的属性信息融合在拓扑图中，定义了节点与社区之间的拓扑势吸引，利用网络相对于前一时刻的改变量不断更新完善当前时刻社区结构。通过在真实网络数据上进行实验仿真，证明此算法能够更有效、更实时地发现有意义的社区结构，并具有较小的时间复杂性。

A Dynamic Community Structure Detection Scheme Based on Social Network Incremental

In the real world, the structure of social networks is not static, but varying with times changing, and the same communities as an essential feature of social networks is also true. An incremental dynamic community detecting algorithm is proposed to reveal the actual communities based attribute weighted networks. It associates attribute information with topology graph and defines topological potential attraction between nodes and communities, using the incremental comparing with previous time to update the current community structure. The experiment on real network data proved that the proposed algorithm could be more effectively and timely to discover meaningful community structure, and having a smaller time complexity.