摘要
提出了Web页面聚类算法PageCluster及相应的改进算法ImPageCluster。该方法在兼顾Web站点结构和页面链接的同时,基于各个页面的重要程度对各个超链接进行赋权。与传统聚类算法相比,该算法不需要事先给定相似度阈值。实验结果证实了该算法的可行性和高效性。
A Web page clustering algorithm called PageCluster,with the improved algorithm called ImPageCluster is proposed.These methods take not only the web structure and page hyperlinks,but also the importance of each page which is described as in-weight and out-weight into account.Compared with the traditional clustering methods,these algorithms don't need to be given the similarity threshold.And the experimental results show that these algorithms are feasible and high-efficient.
出处
《计算机工程与应用》
CSCD
北大核心
2004年第29期84-86,共3页
Computer Engineering and Applications