摘要： 由于Web数据所具有的半结构化特征，基于Web的数据挖掘与传统的基于数据库的数据挖掘有许多不同之处。基于Web的数据挖掘主要包括3种数据挖掘任务：对Web内容的挖掘，对Web结构的挖掘和对Web访问的挖掘。该文综述了基于Web的数据挖掘技术，并介绍了国内在这个领域的研究现状。

关键词: 数据挖掘, 知识获取, 半结构化数据, KDW, Web

Abstract: Web-based data mining, because of the semi-structured data feature, is quite different from the traditional database-based date mining. Web-based data mining includes the data mining of Web content, Web structure and Web usage. This paper makes a survey of Web-based date mining technology, especially the domestic research status in quo.

中图分类号: 

• TP311.12