[{"citation":{"mla":"Henzinger, Monika H. “Algorithmic Challenges in Web Search Engines.” Internet Mathematics, vol. 1, no. 1, Internet Mathematics, 2004, pp. 115–23, doi:10.1080/15427951.2004.10129079.","short":"M.H. Henzinger, Internet Mathematics 1 (2004) 115–123.","ieee":"M. H. Henzinger, “Algorithmic challenges in web search engines,” Internet Mathematics, vol. 1, no. 1. Internet Mathematics, pp. 115–123, 2004.","apa":"Henzinger, M. H. (2004). Algorithmic challenges in web search engines. Internet Mathematics. Internet Mathematics. https://doi.org/10.1080/15427951.2004.10129079","ama":"Henzinger MH. Algorithmic challenges in web search engines. Internet Mathematics. 2004;1(1):115-123. doi:10.1080/15427951.2004.10129079","chicago":"Henzinger, Monika H. “Algorithmic Challenges in Web Search Engines.” Internet Mathematics. Internet Mathematics, 2004. https://doi.org/10.1080/15427951.2004.10129079.","ista":"Henzinger MH. 2004. Algorithmic challenges in web search engines. Internet Mathematics. 1(1), 115–123."},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","article_processing_charge":"No","author":[{"id":"540c9bbd-f2de-11ec-812d-d04a5be85630","first_name":"Monika H","orcid":"0000-0002-5008-6530","full_name":"Henzinger, Monika H","last_name":"Henzinger"}],"title":"Algorithmic challenges in web search engines","year":"2004","publication":"Internet Mathematics","day":"01","page":"115-123","date_created":"2022-08-08T11:55:53Z","doi":"10.1080/15427951.2004.10129079","date_published":"2004-01-01T00:00:00Z","oa":1,"publisher":"Internet Mathematics","quality_controlled":"1","date_updated":"2023-02-10T07:47:21Z","extern":"1","_id":"11762","type":"journal_article","article_type":"original","status":"public","publication_status":"published","publication_identifier":{"eissn":["1944-9488"],"issn":["1542-7951"]},"language":[{"iso":"eng"}],"volume":1,"issue":"1","abstract":[{"lang":"eng","text":"In this paper, we describe six algorithmic problems that arise in web search engines and that are not or only partially solved: (1) Uniformly sampling of web pages; (2) modeling the web graph; (3) finding duplicate hosts; (4) finding top gainers and losers in data streams; (5) finding large dense bipartite graphs; and (6) understanding how eigenvectors partition the web."}],"oa_version":"Published Version","main_file_link":[{"open_access":"1","url":"https://doi.org/10.1080/15427951.2004.10129079"}],"scopus_import":"1","intvolume":" 1","month":"01"},{"volume":3221,"date_published":"2004-09-01T00:00:00Z","doi":"10.1007/978-3-540-30140-0_2","date_created":"2022-08-11T13:18:05Z","page":"3","day":"01","publication":"2th Annual European Symposium on Algorithms","language":[{"iso":"eng"}],"publication_identifier":{"isbn":[" 3540230254"],"eissn":["1611-3349"],"issn":["0302-9743"]},"year":"2004","publication_status":"published","month":"09","intvolume":" 3221","quality_controlled":"1","alternative_title":["LNCS"],"publisher":"Springer Nature","scopus_import":"1","oa_version":"None","abstract":[{"text":"Web search engines have emerged as one of the central applications on the internet. In fact, search has become one of the most important activities that people engage in on the Internet. Even beyond becoming the number one source of information, a growing number of businesses are depending on web search engines for customer acquisition. In this talk I will brief review the history of web search engines: The first generation of web search engines used text-only retrieval techniques. Google revolutionized the field by deploying the PageRank technology – an eigenvector-based analysis of the hyperlink structure- to analyze the web in order to produce relevant results. Moving forward, our goal is to achieve a better understanding of a page with a view towards producing even more relevant results.\r\n\r\nGoogle is powered by a large number of PCs. Using this infrastructure and striving to be as efficient as possible poses challenging systems problems but also various algorithmic challenges. I will discuss some of them in my talk.","lang":"eng"}],"title":"Algorithmic aspects of web search engines","author":[{"last_name":"Henzinger","full_name":"Henzinger, Monika H","orcid":"0000-0002-5008-6530","first_name":"Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630"}],"article_processing_charge":"No","extern":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2023-02-13T11:47:26Z","citation":{"mla":"Henzinger, Monika H. “Algorithmic Aspects of Web Search Engines.” 2th Annual European Symposium on Algorithms, vol. 3221, Springer Nature, 2004, p. 3, doi:10.1007/978-3-540-30140-0_2.","apa":"Henzinger, M. H. (2004). Algorithmic aspects of web search engines. In 2th Annual European Symposium on Algorithms (Vol. 3221, p. 3). Bergen, Norway: Springer Nature. https://doi.org/10.1007/978-3-540-30140-0_2","ama":"Henzinger MH. Algorithmic aspects of web search engines. In: 2th Annual European Symposium on Algorithms. Vol 3221. Springer Nature; 2004:3. doi:10.1007/978-3-540-30140-0_2","short":"M.H. Henzinger, in:, 2th Annual European Symposium on Algorithms, Springer Nature, 2004, p. 3.","ieee":"M. H. Henzinger, “Algorithmic aspects of web search engines,” in 2th Annual European Symposium on Algorithms, Bergen, Norway, 2004, vol. 3221, p. 3.","chicago":"Henzinger, Monika H. “Algorithmic Aspects of Web Search Engines.” In 2th Annual European Symposium on Algorithms, 3221:3. Springer Nature, 2004. https://doi.org/10.1007/978-3-540-30140-0_2.","ista":"Henzinger MH. 2004. Algorithmic aspects of web search engines. 2th Annual European Symposium on Algorithms. ESA: European Symposium on Algorithms, LNCS, vol. 3221, 3."},"status":"public","type":"conference","conference":{"name":"ESA: European Symposium on Algorithms","location":"Bergen, Norway","end_date":"2004-09-17","start_date":"2004-09-14"},"_id":"11801"},{"scopus_import":"1","publisher":"Springer Nature","alternative_title":["LNCS"],"quality_controlled":"1","month":"07","intvolume":" 3142","abstract":[{"lang":"eng","text":"Web search engines have emerged as one of the central applications on the Internet. In fact, search has become one of the most important activities that people engage in on the the Internet. Even beyond becoming the number one source of information, a growing number of businesses are depending on web search engines for customer acquisition.\r\n\r\nThe first generation of web search engines used text-only retrieval techniques. Google revolutionized the field by deploying the PageRank technology – an eigenvector-based analysis of the hyperlink structure – to analyze the web in order to produce relevant results. Moving forward, our goal is to achieve a better understanding of a page with a view towards producing even more relevant results."}],"oa_version":"None","page":"3","volume":3142,"doi":"10.1007/978-3-540-27836-8_2","date_published":"2004-07-01T00:00:00Z","date_created":"2022-08-11T12:38:58Z","publication_identifier":{"issn":["0302-9743"],"eissn":["1611-3349"]},"publication_status":"published","year":"2004","day":"01","publication":"31st International Colloquium on Automata, Languages and Programming","language":[{"iso":"eng"}],"type":"conference","conference":{"name":"ICALP: International Colloquium on Automata, Languages, and Programming","start_date":"2004-07-12","location":"Turku, Finland","end_date":"2004-07-16"},"status":"public","_id":"11800","author":[{"first_name":"Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630","last_name":"Henzinger","full_name":"Henzinger, Monika H","orcid":"0000-0002-5008-6530"}],"article_processing_charge":"No","title":"The past, present, and future of web search engines","citation":{"chicago":"Henzinger, Monika H. “The Past, Present, and Future of Web Search Engines.” In 31st International Colloquium on Automata, Languages and Programming, 3142:3. Springer Nature, 2004. https://doi.org/10.1007/978-3-540-27836-8_2.","ista":"Henzinger MH. 2004. The past, present, and future of web search engines. 31st International Colloquium on Automata, Languages and Programming. ICALP: International Colloquium on Automata, Languages, and Programming, LNCS, vol. 3142, 3.","mla":"Henzinger, Monika H. “The Past, Present, and Future of Web Search Engines.” 31st International Colloquium on Automata, Languages and Programming, vol. 3142, Springer Nature, 2004, p. 3, doi:10.1007/978-3-540-27836-8_2.","short":"M.H. Henzinger, in:, 31st International Colloquium on Automata, Languages and Programming, Springer Nature, 2004, p. 3.","ieee":"M. H. Henzinger, “The past, present, and future of web search engines,” in 31st International Colloquium on Automata, Languages and Programming, Turku, Finland, 2004, vol. 3142, p. 3.","ama":"Henzinger MH. The past, present, and future of web search engines. In: 31st International Colloquium on Automata, Languages and Programming. Vol 3142. Springer Nature; 2004:3. doi:10.1007/978-3-540-27836-8_2","apa":"Henzinger, M. H. (2004). The past, present, and future of web search engines. In 31st International Colloquium on Automata, Languages and Programming (Vol. 3142, p. 3). Turku, Finland: Springer Nature. https://doi.org/10.1007/978-3-540-27836-8_2"},"date_updated":"2023-02-13T11:45:25Z","extern":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87"},{"abstract":[{"text":"In this article we describe the approach taken by the first web search engines, discuss the state of the art, and present some of the challenges for the future.","lang":"eng"}],"oa_version":"None","publisher":"Society of Photo-Optical Instrumentation Engineers","scopus_import":"1","quality_controlled":"1","intvolume":" 5296","month":"01","year":"2004","publication_status":"published","publication_identifier":{"issn":["0277-786X"]},"language":[{"iso":"eng"}],"publication":"SPIE Proceedings","day":"01","page":"23 - 26","date_created":"2022-08-16T08:46:41Z","date_published":"2004-01-01T00:00:00Z","doi":"10.1117/12.537534","volume":5296,"_id":"11859","conference":{"location":"San Jose, CA, United States","end_date":"2004-01-22","start_date":"2004-01-21","name":"Document Recognition and Retrieval XI"},"type":"conference","status":"public","citation":{"chicago":"Henzinger, Monika H. “The Past, Present, and Future of Web Information Retrieval.” In SPIE Proceedings, 5296:23–26. Society of Photo-Optical Instrumentation Engineers, 2004. https://doi.org/10.1117/12.537534.","ista":"Henzinger MH. 2004. The past, present, and future of web information retrieval. SPIE Proceedings. Document Recognition and Retrieval XI vol. 5296, 23–26.","mla":"Henzinger, Monika H. “The Past, Present, and Future of Web Information Retrieval.” SPIE Proceedings, vol. 5296, Society of Photo-Optical Instrumentation Engineers, 2004, pp. 23–26, doi:10.1117/12.537534.","short":"M.H. Henzinger, in:, SPIE Proceedings, Society of Photo-Optical Instrumentation Engineers, 2004, pp. 23–26.","ieee":"M. H. Henzinger, “The past, present, and future of web information retrieval,” in SPIE Proceedings, San Jose, CA, United States, 2004, vol. 5296, pp. 23–26.","ama":"Henzinger MH. The past, present, and future of web information retrieval. In: SPIE Proceedings. Vol 5296. Society of Photo-Optical Instrumentation Engineers; 2004:23-26. doi:10.1117/12.537534","apa":"Henzinger, M. H. (2004). The past, present, and future of web information retrieval. In SPIE Proceedings (Vol. 5296, pp. 23–26). San Jose, CA, United States: Society of Photo-Optical Instrumentation Engineers. https://doi.org/10.1117/12.537534"},"date_updated":"2023-02-17T10:05:19Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","extern":"1","article_processing_charge":"No","author":[{"id":"540c9bbd-f2de-11ec-812d-d04a5be85630","first_name":"Monika H","full_name":"Henzinger, Monika H","orcid":"0000-0002-5008-6530","last_name":"Henzinger"}],"title":"The past, present, and future of web information retrieval"},{"date_created":"2022-08-16T13:06:10Z","date_published":"2004-04-06T00:00:00Z","doi":"10.1073/pnas.0307528100","page":"5186-5191","publication":"Proceedings of the National Academy of Sciences","day":"06","year":"2004","oa":1,"quality_controlled":"1","publisher":"Proceedings of the National Academy of Sciences","title":"Extracting knowledge from the World Wide Web","external_id":{"pmid":["14745041"]},"article_processing_charge":"No","author":[{"full_name":"Henzinger, Monika H","orcid":"0000-0002-5008-6530","last_name":"Henzinger","first_name":"Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630"},{"full_name":"Lawrence, Steve","last_name":"Lawrence","first_name":"Steve"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"ama":"Henzinger MH, Lawrence S. Extracting knowledge from the World Wide Web. Proceedings of the National Academy of Sciences. 2004;101(suppl_1):5186-5191. doi:10.1073/pnas.0307528100","apa":"Henzinger, M. H., & Lawrence, S. (2004). Extracting knowledge from the World Wide Web. Proceedings of the National Academy of Sciences. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.0307528100","ieee":"M. H. Henzinger and S. Lawrence, “Extracting knowledge from the World Wide Web,” Proceedings of the National Academy of Sciences, vol. 101, no. suppl_1. Proceedings of the National Academy of Sciences, pp. 5186–5191, 2004.","short":"M.H. Henzinger, S. Lawrence, Proceedings of the National Academy of Sciences 101 (2004) 5186–5191.","mla":"Henzinger, Monika H., and Steve Lawrence. “Extracting Knowledge from the World Wide Web.” Proceedings of the National Academy of Sciences, vol. 101, no. suppl_1, Proceedings of the National Academy of Sciences, 2004, pp. 5186–91, doi:10.1073/pnas.0307528100.","ista":"Henzinger MH, Lawrence S. 2004. Extracting knowledge from the World Wide Web. Proceedings of the National Academy of Sciences. 101(suppl_1), 5186–5191.","chicago":"Henzinger, Monika H, and Steve Lawrence. “Extracting Knowledge from the World Wide Web.” Proceedings of the National Academy of Sciences. Proceedings of the National Academy of Sciences, 2004. https://doi.org/10.1073/pnas.0307528100."},"volume":101,"issue":"suppl_1","language":[{"iso":"eng"}],"publication_status":"published","publication_identifier":{"issn":["0027-8424"],"eissn":["1091-6490"]},"intvolume":" 101","month":"04","main_file_link":[{"open_access":"1","url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC387294/"}],"scopus_import":"1","pmid":1,"oa_version":"Published Version","abstract":[{"lang":"eng","text":"The World Wide Web provides a unprecedented opportunity to automatically analyze a large sample of interests and activity in the world. We discuss methods for extracting knowledge from the web by randomly sampling and analyzing hosts and pages, and by analyzing the link structure of the web and how links accumulate over time. A variety of interesting and valuable information can be extracted, such as the distribution of web pages over domains, the distribution of interest in different areas, communities related to different topics, the nature of competition in different categories of sites, and the degree of communication between different communities or countries."}],"extern":"1","date_updated":"2023-02-17T12:21:43Z","status":"public","type":"journal_article","article_type":"original","_id":"11877"}]