[{"publication_identifier":{"issn":["1389-1286"]},"doi":"10.1016/s1389-1286(00)00055-4","scopus_import":"1","oa_version":"None","month":"06","language":[{"iso":"eng"}],"date_updated":"2024-11-06T08:11:55Z","author":[{"full_name":"Henzinger, Monika H","last_name":"Henzinger","id":"540c9bbd-f2de-11ec-812d-d04a5be85630","first_name":"Monika H","orcid":"0000-0002-5008-6530"},{"full_name":"Heydon, Allan","last_name":"Heydon","first_name":"Allan"},{"full_name":"Mitzenmacher, Michael","last_name":"Mitzenmacher","first_name":"Michael"},{"full_name":"Najork, Marc","last_name":"Najork","first_name":"Marc"}],"date_published":"2000-06-01T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"On near-uniform URL sampling","citation":{"ista":"Henzinger M, Heydon A, Mitzenmacher M, Najork M. 2000. On near-uniform URL sampling. Computer Networks. 33(1–6), 295–308.","ama":"Henzinger M, Heydon A, Mitzenmacher M, Najork M. On near-uniform URL sampling. <i>Computer Networks</i>. 2000;33(1-6):295-308. doi:<a href=\"https://doi.org/10.1016/s1389-1286(00)00055-4\">10.1016/s1389-1286(00)00055-4</a>","chicago":"Henzinger, Monika, Allan Heydon, Michael Mitzenmacher, and Marc Najork. “On Near-Uniform URL Sampling.” <i>Computer Networks</i>. Elsevier, 2000. <a href=\"https://doi.org/10.1016/s1389-1286(00)00055-4\">https://doi.org/10.1016/s1389-1286(00)00055-4</a>.","apa":"Henzinger, M., Heydon, A., Mitzenmacher, M., &#38; Najork, M. (2000). On near-uniform URL sampling. <i>Computer Networks</i>. Elsevier. <a href=\"https://doi.org/10.1016/s1389-1286(00)00055-4\">https://doi.org/10.1016/s1389-1286(00)00055-4</a>","mla":"Henzinger, Monika, et al. “On Near-Uniform URL Sampling.” <i>Computer Networks</i>, vol. 33, no. 1–6, Elsevier, 2000, pp. 295–308, doi:<a href=\"https://doi.org/10.1016/s1389-1286(00)00055-4\">10.1016/s1389-1286(00)00055-4</a>.","ieee":"M. Henzinger, A. Heydon, M. Mitzenmacher, and M. Najork, “On near-uniform URL sampling,” <i>Computer Networks</i>, vol. 33, no. 1–6. Elsevier, pp. 295–308, 2000.","short":"M. Henzinger, A. Heydon, M. Mitzenmacher, M. Najork, Computer Networks 33 (2000) 295–308."},"quality_controlled":"1","article_type":"original","date_created":"2022-07-28T15:11:53Z","year":"2000","volume":33,"day":"01","keyword":["URL sampling","Random walks","Internet domain distribution","Search engine size"],"page":"295-308","type":"journal_article","article_processing_charge":"No","extern":"1","issue":"1-6","publication":"Computer Networks","publisher":"Elsevier","abstract":[{"lang":"eng","text":"We consider the problem of sampling URLs uniformly at random from the Web. A tool for sampling URLs uniformly can be used to estimate various properties of Web pages, such as the fraction of pages in various Internet domains or written in various languages. Moreover, uniform URL sampling can be used to determine the sizes of various search engines relative to the entire Web. In this paper, we consider sampling approaches based on random walks of the Web graph. In particular, we suggest ways of improving sampling based on random walks to make the samples closer to uniform. We suggest a natural test bed based on random graphs for testing the effectiveness of our procedures. We then use our sampling approach to estimate the distribution of pages over various Internet domains and to estimate the coverage of various search engine indexes."}],"_id":"11685","intvolume":"        33","status":"public","publication_status":"published"},{"publication_identifier":{"issn":["1389-1286"]},"doi":"10.1016/s1389-1286(99)00022-5","oa_version":"None","scopus_import":"1","month":"05","language":[{"iso":"eng"}],"date_updated":"2024-11-06T12:08:44Z","author":[{"full_name":"Dean, Jeffrey","last_name":"Dean","first_name":"Jeffrey"},{"orcid":"0000-0002-5008-6530","first_name":"Monika H","last_name":"Henzinger","full_name":"Henzinger, Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630"}],"date_published":"1999-05-17T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"Finding related pages in the world wide Web","citation":{"mla":"Dean, Jeffrey, and Monika Henzinger. “Finding Related Pages in the World Wide Web.” <i>Computer Networks</i>, vol. 31, no. 11–16, Elsevier, 1999, pp. 1467–79, doi:<a href=\"https://doi.org/10.1016/s1389-1286(99)00022-5\">10.1016/s1389-1286(99)00022-5</a>.","short":"J. Dean, M. Henzinger, Computer Networks 31 (1999) 1467–1479.","ieee":"J. Dean and M. Henzinger, “Finding related pages in the world wide Web,” <i>Computer Networks</i>, vol. 31, no. 11–16. Elsevier, pp. 1467–1479, 1999.","apa":"Dean, J., &#38; Henzinger, M. (1999). Finding related pages in the world wide Web. <i>Computer Networks</i>. Elsevier. <a href=\"https://doi.org/10.1016/s1389-1286(99)00022-5\">https://doi.org/10.1016/s1389-1286(99)00022-5</a>","chicago":"Dean, Jeffrey, and Monika Henzinger. “Finding Related Pages in the World Wide Web.” <i>Computer Networks</i>. Elsevier, 1999. <a href=\"https://doi.org/10.1016/s1389-1286(99)00022-5\">https://doi.org/10.1016/s1389-1286(99)00022-5</a>.","ama":"Dean J, Henzinger M. Finding related pages in the world wide Web. <i>Computer Networks</i>. 1999;31(11-16):1467-1479. doi:<a href=\"https://doi.org/10.1016/s1389-1286(99)00022-5\">10.1016/s1389-1286(99)00022-5</a>","ista":"Dean J, Henzinger M. 1999. Finding related pages in the world wide Web. Computer Networks. 31(11–16), 1467–1479."},"article_type":"original","quality_controlled":"1","year":"1999","date_created":"2022-07-29T06:55:26Z","day":"17","page":"1467-1479","keyword":["Search engines","Related pages","Searching paradigms"],"volume":31,"type":"journal_article","article_processing_charge":"No","publisher":"Elsevier","publication":"Computer Networks","issue":"11-16","extern":"1","status":"public","abstract":[{"lang":"eng","text":"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.\r\n\r\nWe 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."}],"intvolume":"        31","_id":"11687","publication_status":"published"},{"publication_status":"published","_id":"11688","intvolume":"        31","abstract":[{"lang":"eng","text":"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."}],"status":"public","article_processing_charge":"No","publication":"Computer Networks","issue":"11-16","extern":"1","publisher":"Elsevier","volume":31,"keyword":["Search engines","Index quality","Random walks","PageRank"],"page":"1291-1303","day":"17","type":"journal_article","quality_controlled":"1","article_type":"original","date_created":"2022-07-29T07:00:28Z","year":"1999","citation":{"ieee":"M. Henzinger, A. Heydon, M. Mitzenmacher, and M. Najork, “Measuring index quality using random walks on the web,” <i>Computer Networks</i>, vol. 31, no. 11–16. Elsevier, pp. 1291–1303, 1999.","mla":"Henzinger, Monika, et al. “Measuring Index Quality Using Random Walks on the Web.” <i>Computer Networks</i>, vol. 31, no. 11–16, Elsevier, 1999, pp. 1291–303, doi:<a href=\"https://doi.org/10.1016/s1389-1286(99)00016-x\">10.1016/s1389-1286(99)00016-x</a>.","short":"M. Henzinger, A. Heydon, M. Mitzenmacher, M. Najork, Computer Networks 31 (1999) 1291–1303.","chicago":"Henzinger, Monika, Allan Heydon, Michael Mitzenmacher, and Marc Najork. “Measuring Index Quality Using Random Walks on the Web.” <i>Computer Networks</i>. Elsevier, 1999. <a href=\"https://doi.org/10.1016/s1389-1286(99)00016-x\">https://doi.org/10.1016/s1389-1286(99)00016-x</a>.","apa":"Henzinger, M., Heydon, A., Mitzenmacher, M., &#38; Najork, M. (1999). Measuring index quality using random walks on the web. <i>Computer Networks</i>. Elsevier. <a href=\"https://doi.org/10.1016/s1389-1286(99)00016-x\">https://doi.org/10.1016/s1389-1286(99)00016-x</a>","ista":"Henzinger M, Heydon A, Mitzenmacher M, Najork M. 1999. Measuring index quality using random walks on the web. Computer Networks. 31(11–16), 1291–1303.","ama":"Henzinger M, Heydon A, Mitzenmacher M, Najork M. Measuring index quality using random walks on the web. <i>Computer Networks</i>. 1999;31(11-16):1291-1303. doi:<a href=\"https://doi.org/10.1016/s1389-1286(99)00016-x\">10.1016/s1389-1286(99)00016-x</a>"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"Measuring index quality using random walks on the web","author":[{"first_name":"Monika H","orcid":"0000-0002-5008-6530","full_name":"Henzinger, Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630","last_name":"Henzinger"},{"first_name":"Allan","full_name":"Heydon, Allan","last_name":"Heydon"},{"last_name":"Mitzenmacher","full_name":"Mitzenmacher, Michael","first_name":"Michael"},{"last_name":"Najork","full_name":"Najork, Marc","first_name":"Marc"}],"date_published":"1999-05-17T00:00:00Z","date_updated":"2024-11-06T08:14:12Z","language":[{"iso":"eng"}],"oa_version":"None","scopus_import":"1","month":"05","doi":"10.1016/s1389-1286(99)00016-x","publication_identifier":{"issn":["1389-1286"]}}]