语义相似的PageRank改进算法

New semantic similarity PageRank algorithm

PageRank算法是一种用于网页排序的算法,它利用网页间的相互引用关系评价网页的重要性。但由于它只考虑网页与网页之间的链接结构,忽略了网页与主题的相关性,容易造成主题漂移现象。在分析了原PageRank算法基础上,给出了一种基于语义相似度的PageRank改进算法。该算法能够按照网页结构和网页主要内容计算出网页的PageRank值,既不会增加算法的时空复杂度,又极大地减少了"主题漂移"现象,从而提高查询效率和质量。

The PageRank algorithm is used in ranking web pages.It estimates the pages’authority by taking into account the link web structure.However,it only considers the structure of webs’link,without any topic about webs,so this algorithm leads to topic-drift.After analyzing the original PageRank algorithm several times,an improved PageRank algorithm based on semantic simi-larity is proposed.This new PageRank algorithm can calculate the PageRank’s value according to the structure and content about web,it can avoid the topic-drift problem and improve the quality of web search effectively without adding any other extra time and space complexity degree.