基于Hyperlink和相关度发现Web相关文档的研究

Finding Relevant Documents Using Hyperlink and Similarity Measure on the Web

分析了 Web文档的相似度计算方法 ,提出了 Web上查询相关信息发现的 SW- HITS算法 ,它结合了 Web超链接、网页知识表示的信息相关度以及 HITS方法来搜索 Web上相关知识 .本文通过它们搜索网上有关医药的信息和知识 ,其效果和查准率比传统 HITS和

In this paper we discuss Similarity Weighted HITS (SW HITS) algorithms in finding relevant documents on the Web. These methods not only use the hyperlinks of web graph, but also the similarity scoring of term weights in document representations. We implement the algorithm to find Chinese medical information from the Internet. Our study showed that it has better precision than traditional IR methods and basic HITS alogorithms.