一种基于用户浏览路径的Web用户聚类方法  

Clustering Web Users Based on Users' Browsing Path

作　　者：马晓艳[1] 唐雁[1] 

机构地区：[1]西南大学计算机与信息科学学院,重庆400715

出　　处：《西南师范大学学报（自然科学版）》2009年第3期93-97,共5页Journal of Southwest China Normal University(Natural Science Edition)

摘　　要：在Web用户聚类中,针对具有相似浏览路径和兴趣的用户聚类问题,提出一种新的相似度计算方法.该方法将事务路径看作有序时间序列,以代替用户的兴趣路径;同时结合用户事务路径的停留时间来计算相似度.通过这种方法计算出的用户相似度更接近真实,达到提高Web用户聚类的效果,为用户提供更优质的个性化服务.对比实验证明该方法的有效性.This paper presents a new method of calculating the similarity according to Web user clustering where they got the similar interests and acts of the path. The method takes acts of path as a numerical time series in place of the user interesting path. at the same time, the method calculates the similarity according to length of the time the user elapsed in the Web pages, and this maks the clustering more precise as well as better clustering results. Its effectiveness was proved true by the comparison experiment too.

关 键 词：WEB日志挖掘 相似度 用户聚类 事务路径 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]