Research on the Design and Key Techniques of Web Mining System
Xue Hong-min · 2005
Web mining is a new research area and involves several research communities, such as ML, DM, IR, NLP, DB and AI. It can be used in Web retrieval, web sites construction and e-commerce etc. Based on the whole study of Web mining techniques, a general architecture of Web mining system has been presented. The techniques, research issues and resolution of each component, resource finding, information selection and preprocessing, pattern discovery and pattern analysis, are also discussed in details. This paper introduced a smart web page gather-WebCrawler which takes both the text and structure information into account and gets the excellent pages of the web.