Finding Related Web Pages Based on Connectivity Information from a Search Engine
Finding Related Web Pages Based on Connectivity Information from a Search Engine
复制标题
根据搜索引擎的连接信息查找相关网页
DOI：
--
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
T. Murata
中科院分区：
文献类型：
--
作者：
T. Murata
tmurata@nii.ac.jp摘要提出了一种基于超链接连通性信息的相关网页查找方法. Kumar认为，一个完全的二分图可以看作是一个有共同兴趣的Web社区。然而，准备Web快照数据用于搜索这样的社区并不是一件容易的事情，因为Web是巨大的，并且正在增长。在我们的方法中，连接信息是从搜索引擎获得的反向链接搜索。基于该方法的系统成功地发现几个流派的Web社区，只有从少数输入的URL，而不分析网页的内容。
tmurata@nii.ac.jp ABSTRACT This paper proposes a method for finding related Web pages based on connectivity information of hyperlinks. As claimed by Kumar, a complete bipartite graph of Web pages can be regarded as a Web community sharing a common interest. However, preparing Web snapshot data for the search of such communities is not an easy task since the Web is huge and is growing. In our method, connectivity information is acquired from a search engine by backlink search. A system based on the method succeeds in finding several genres of Web communities only from a few input URLs without analyzing the contents of Web pages.