@article{11687,
  abstract     = {When using traditional search engines, users have to formulate queries to describe their information need. This paper discusses a different approach to Web searching where the input to the search process is not a set of query terms, but instead is the URL of a page, and the output is a set of related Web pages. A related Web page is one that addresses the same topic as the original page. For example, www.washingtonpost.com is a page related to www.nytimes.com, since both are online newspapers.

We describe two algorithms to identify related Web pages. These algorithms use only the connectivity information in the Web (i.e., the links between pages) and not the content of pages or usage information. We have implemented both algorithms and measured their runtime performance. To evaluate the effectiveness of our algorithms, we performed a user study comparing our algorithms with Netscape's `What's Related' service (http://home.netscape.com/escapes/related/). Our study showed that the precision at 10 for our two algorithms are 73% better and 51% better than that of Netscape, despite the fact that Netscape uses both content and usage pattern information in addition to connectivity information.},
  author       = {Dean, Jeffrey and Henzinger, Monika H},
  issn         = {1389-1286},
  journal      = {Computer Networks},
  keywords     = {Search engines, Related pages, Searching paradigms},
  number       = {11-16},
  pages        = {1467--1479},
  publisher    = {Elsevier},
  title        = {{Finding related pages in the world wide Web}},
  doi          = {10.1016/s1389-1286(99)00022-5},
  volume       = {31},
  year         = {1999},
}

@article{11688,
  abstract     = {Recent research has studied how to measure the size of a search engine, in terms of the number of pages indexed. In this paper, we consider a different measure for search engines, namely the quality of the pages in a search engine index. We provide a simple, effective algorithm for approximating the quality of an index by performing a random walk on the Web, and we use this methodology to compare the index quality of several major search engines.},
  author       = {Henzinger, Monika H and Heydon, Allan and Mitzenmacher, Michael and Najork, Marc},
  issn         = {1389-1286},
  journal      = {Computer Networks},
  keywords     = {Search engines, Index quality, Random walks, PageRank},
  number       = {11-16},
  pages        = {1291--1303},
  publisher    = {Elsevier},
  title        = {{Measuring index quality using random walks on the web}},
  doi          = {10.1016/s1389-1286(99)00016-x},
  volume       = {31},
  year         = {1999},
}