| Web访问挖掘中事务聚类研究 |
| |
| 引用本文： | 朱霞,殷凯,黄树成. Web访问挖掘中事务聚类研究[J]. 常州工学院学报, 2004, 17(6): 45-49 |
| |
| 作者姓名： | 朱霞 殷凯 黄树成 |
| |
| 作者单位： | 常州工学院外国语学院,江苏,常州,213002;常州工学院计算机信息工程学院,江苏,常州,213002 |
| |
| 摘 要： | Web访问挖掘可以发现用户浏览Web的目标、兴趣等行为模式,使Web变得更容易获取信息。聚类分析是Web访问挖掘系统的重要组件,聚类分析的质量决定挖掘结果的有效性。现有的三类聚类算法具有各自的缺点,本文概述了三种算法,给出了一种基于广义后缀树的聚类算法,通过实例说明了它的原理和优点。
|
| 关 键 词： | Web访问挖掘 聚类 |
| 文章编号： | 1671-0436(2004)06-0045-05 |
| 修稿时间： | 2004-08-30 |
Research on Clustering in Web Access Mining |
| |
| ZHU Xia YIN Kai HUANG Shu-cheng. Research on Clustering in Web Access Mining[J]. Journal of Changzhou Institute of Technology, 2004, 17(6): 45-49 |
| |
| Authors: | ZHU Xia YIN Kai HUANG Shu-cheng |
| |
| Abstract: | Web access Mining, which mines user's objective, interesting content and behaviour habits turns Web easy for user finding information. Clustering analysis is an important component of Web access mining system, whose quality determines validity of mining results. The paper outlines three current clustering algorithms which have shortcoming respectively. It proposes a broad - suffix tree based algorithm and instantiates its principles and fortes |
| |
| Keywords: | Web access mining clustering. |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
