Abstract:

As the rapid development of the Internet, the technology of Web mining is now a hotter research field of data mining. This paper discusses the characteristics and methods of Web mining, and gives a fast and efficient Web document clustering method. It gives the experiment, which shows that the technology of Web mining is practical and efficient. The technology is suitable for the system and affords more guarantee and reliability.

Key words: Web mining, Log file, Document clustering, Vector space model(VSM), Association rule

摘要：

随着互联网的飞速发展，Web挖掘技术已成为数据挖掘技术的一个研究热点。该文对Web挖掘的特点、方法进行了讨论，设计了一种快速有效的Web文档聚类方法，给出了实际测试结果，验证了Web挖掘技术的有效性。提出的Web挖掘技术有效地提高了该系统的协作能力。

关键词: Web挖掘, 日志文件, 文档聚类, 矢量空间模型, 关联规则

CLC Number: 

• TP391