一种基于流量的Web社区挖掘方法  

A flow-based method for mining web communities

作　　者：张永平[1] 丰志刚[2] 李从东[1] 

机构地区：[1]天津大学管理学院,天津300000 [2]燕山大学信息科学与工程学院,河北秦皇岛066004

出　　处：《燕山大学学报》2007年第5期418-421,437,共5页Journal of Yanshan University

摘　　要：Web社区是由对于同一主题感兴趣的人或组织创作的Web页的集合。提出了一种比较严格的Web社区表示法,同时对社区内和社区外的节点进行约束,解决了以往社区定义边界模糊的问题。设计了与该定义对应的Web社区挖掘算法。算法充分考虑了Web图的性质,并在构造好的网络流上采用最大流/最小割算法,从而得到所要的社区。实验表明,该方法可以挖掘出较大而且有意义的社区。Web community is a collection of web pages shared by individuals or organizations. A stricter web community definition is introduced, in which both inside vertices and outside vertices of a community are conditioned, to overcome boundary ambiguity of other web community definitions. A web community mining algorithm is designed according to our definition, which thinks of the properties of the web, uses maximum flow/minimum cut algorithm in the network flow constructed, and then the web community is found. The result demonstrates that the proposed approach can mine out big meaningful communities.

关 键 词：WEB社区 WEB挖掘 最大流/最小割算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]