{"id":"https://openalex.org/W1599368672","doi":"https://doi.org/10.1007/978-3-642-03079-6_15","title":"Frequent Itemset Mining for Clustering Near Duplicate Web Documents","display_name":"Frequent Itemset Mining for Clustering Near Duplicate Web Documents","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1599368672","doi":"https://doi.org/10.1007/978-3-642-03079-6_15","mag":"1599368672"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-03079-6_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-03079-6_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"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/A5002385420","display_name":"Dmitry I. Ignatov","orcid":"https://orcid.org/0000-0002-6584-8534"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry I. Ignatov","raw_affiliation_strings":["Department of Applied Mathematics, Higher School of Economics, Kirpichnaya 33/5, Moscow, 105679, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Higher School of Economics, Kirpichnaya 33/5, Moscow, 105679, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004960011","display_name":"Sergei O. Kuznetsov","orcid":"https://orcid.org/0000-0003-3284-9001"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergei O. Kuznetsov","raw_affiliation_strings":["Department of Applied Mathematics, Higher School of Economics, Kirpichnaya 33/5, Moscow, 105679, Russia","Higher School of Economics, Department of Applied Mathematics and Information Science, State University, Kirpichnaya 33/5, 105679, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Higher School of Economics, Kirpichnaya 33/5, Moscow, 105679, Russia","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Higher School of Economics, Department of Applied Mathematics and Information Science, State University, Kirpichnaya 33/5, 105679, Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.2006,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91740227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5662","issue":null,"first_page":"185","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.8625214099884033},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6815348863601685},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6061071157455444},{"id":"https://openalex.org/keywords/biclustering","display_name":"Biclustering","score":0.5116255879402161},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5053566098213196},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.48781636357307434},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45175424218177795},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.41495972871780396},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3290417194366455},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2784665822982788},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.16957852244377136},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.1553766131401062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15424180030822754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625214099884033},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6815348863601685},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6061071157455444},{"id":"https://openalex.org/C144817290","wikidata":"https://www.wikidata.org/wiki/Q2976575","display_name":"Biclustering","level":5,"score":0.5116255879402161},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5053566098213196},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.48781636357307434},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45175424218177795},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.41495972871780396},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3290417194366455},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2784665822982788},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.16957852244377136},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.1553766131401062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15424180030822754},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-03079-6_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-03079-6_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"mag:2594505490","is_oa":false,"landing_page_url":"https://publications.hse.ru/en/articles/72111029","pdf_url":null,"source":{"id":"https://openalex.org/S4306518344","display_name":"Lecture Notes in Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Lecture Notes in Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W85121894","https://openalex.org/W159524162","https://openalex.org/W1503729935","https://openalex.org/W1506957411","https://openalex.org/W1532192443","https://openalex.org/W1536700701","https://openalex.org/W1542978828","https://openalex.org/W1830725475","https://openalex.org/W1941707302","https://openalex.org/W1991800036","https://openalex.org/W2057682468","https://openalex.org/W2061779725","https://openalex.org/W2065253760","https://openalex.org/W2066771339","https://openalex.org/W2067432306","https://openalex.org/W2081193615","https://openalex.org/W2087962968","https://openalex.org/W2097184821","https://openalex.org/W2105362912","https://openalex.org/W2128605078","https://openalex.org/W2132069633","https://openalex.org/W2148885851","https://openalex.org/W2153180170","https://openalex.org/W2162495634","https://openalex.org/W2169189540","https://openalex.org/W2788176369","https://openalex.org/W3205240624","https://openalex.org/W4250366158","https://openalex.org/W4255318870","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2611629964","https://openalex.org/W2113284213","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2083329789","https://openalex.org/W2387982377"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}