{"id":"https://openalex.org/W30457518","doi":null,"title":"Clustering web documents: a phrase-based method for grouping search engine results","display_name":"Clustering web documents: a phrase-based method for grouping search engine results","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W30457518","mag":"30457518"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.649","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://turing.cs.washington.edu/papers/zamir_thesis.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069363205","display_name":"Oren Zamir","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oren Zamir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110184338","display_name":"Oren Etzioni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oren Etzioni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8982,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.90755551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.5713000297546387,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.5713000297546387,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.32519999146461487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.04919999837875366,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-document-clustering","display_name":"web page clustering","score":0.9340000152587891},{"id":"https://openalex.org/keywords/search-engine-result-pages","display_name":"search engine results","score":0.9369999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054949998855591},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6659971475601196},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6084949970245361},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5738752484321594},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5102295875549316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47431397438049316},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3519442081451416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32614612579345703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2864220142364502}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.649","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://turing.cs.washington.edu/papers/zamir_thesis.pdf","raw_type":"text"},{"id":"mag:30457518","doi":null,"is_oa":false,"landing_page_url":"http://turing.cs.washington.edu/papers/zamir_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W11171803","https://openalex.org/W28470166","https://openalex.org/W85902540","https://openalex.org/W132406323","https://openalex.org/W193694492","https://openalex.org/W296127572","https://openalex.org/W1481643611","https://openalex.org/W1482472192","https://openalex.org/W1483679765","https://openalex.org/W1484413656","https://openalex.org/W1519852910","https://openalex.org/W1521439890","https://openalex.org/W1524704912","https://openalex.org/W1530378878","https://openalex.org/W1550771877","https://openalex.org/W1570542661","https://openalex.org/W1586180959","https://openalex.org/W1755193636","https://openalex.org/W1853800330","https://openalex.org/W1854214752","https://openalex.org/W1864657091","https://openalex.org/W1971285215","https://openalex.org/W1974820763","https://openalex.org/W1975152892","https://openalex.org/W1978394996","https://openalex.org/W1979280207","https://openalex.org/W1990061958","https://openalex.org/W1990517717","https://openalex.org/W1992249776","https://openalex.org/W1992880122","https://openalex.org/W1995552834","https://openalex.org/W1996764654","https://openalex.org/W2008375984","https://openalex.org/W2013073142","https://openalex.org/W2017661493","https://openalex.org/W2020662977","https://openalex.org/W2022828110","https://openalex.org/W2028342611","https://openalex.org/W2037965136","https://openalex.org/W2040058125","https://openalex.org/W2041565863","https://openalex.org/W2046878543","https://openalex.org/W2047860186","https://openalex.org/W2052899946","https://openalex.org/W2058089741","https://openalex.org/W2059513841","https://openalex.org/W2066165316","https://openalex.org/W2066258442","https://openalex.org/W2066636486","https://openalex.org/W2071172532","https://openalex.org/W2074011351","https://openalex.org/W2074449313","https://openalex.org/W2079533881","https://openalex.org/W2084048649","https://openalex.org/W2085391968","https://openalex.org/W2085685753","https://openalex.org/W2091061212","https://openalex.org/W2097333193","https://openalex.org/W2098162425","https://openalex.org/W2100399036","https://openalex.org/W2100958137","https://openalex.org/W2101740575","https://openalex.org/W2104766360","https://openalex.org/W2112194041","https://openalex.org/W2121252285","https://openalex.org/W2121317427","https://openalex.org/W2126502509","https://openalex.org/W2131687179","https://openalex.org/W2138621811","https://openalex.org/W2141115288","https://openalex.org/W2146828327","https://openalex.org/W2151572224","https://openalex.org/W2151664495","https://openalex.org/W2152565070","https://openalex.org/W2155033358","https://openalex.org/W2158231614","https://openalex.org/W2158874082","https://openalex.org/W2169353895","https://openalex.org/W2169766861","https://openalex.org/W2196501509","https://openalex.org/W2216446631","https://openalex.org/W2533248932","https://openalex.org/W2610179052","https://openalex.org/W2738227713","https://openalex.org/W2914866334","https://openalex.org/W4235036218","https://openalex.org/W4245322178"],"related_works":["https://openalex.org/W2921482105","https://openalex.org/W7097715727","https://openalex.org/W1563459763","https://openalex.org/W7098770553","https://openalex.org/W1603133052","https://openalex.org/W1521439890","https://openalex.org/W2369710579","https://openalex.org/W7100014938","https://openalex.org/W7100764600","https://openalex.org/W2999994935"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}