{"id":"https://openalex.org/W2020390616","doi":"https://doi.org/10.1109/grc.2008.4664707","title":"A fast chinese web-document clustering method under Pareto’s Principle","display_name":"A fast chinese web-document clustering method under Pareto’s Principle","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2020390616","doi":"https://doi.org/10.1109/grc.2008.4664707","mag":"2020390616"},"language":"en","primary_location":{"id":"doi:10.1109/grc.2008.4664707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grc.2008.4664707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Granular Computing","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Zhang Tianlei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhang Tianlei","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, Beijing, China","Dept-of Computer Science and Technology, Tsinghua University, Beijing,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept-of Computer Science and Technology, Tsinghua University, Beijing,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097584967","display_name":"Chen Guishen","orcid":null},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Guishen","raw_affiliation_strings":["Institute of Beijing Electronic System Engineering, Beijing, China","Inst. of Beijing Electron. Syst. Eng., Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Beijing Electronic System Engineering, Beijing, China","institution_ids":["https://openalex.org/I202334528"]},{"raw_affiliation_string":"Inst. of Beijing Electron. Syst. Eng., Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112489758","display_name":"Hao Che","orcid":"https://orcid.org/0009-0001-9852-320X"},"institutions":[{"id":"https://openalex.org/I49496784","display_name":"Beijing City University","ror":"https://ror.org/01jfjwr55","country_code":"CN","type":"education","lineage":["https://openalex.org/I49496784"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Che Hao","raw_affiliation_strings":["Artificial Intelligence Institute, Beijing City University, Beijing, China","Artificial Intell. Inst., Beijing City Univ., Beijing"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Beijing City University, Beijing, China","institution_ids":["https://openalex.org/I49496784"]},{"raw_affiliation_string":"Artificial Intell. Inst., Beijing City Univ., Beijing","institution_ids":["https://openalex.org/I49496784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0736758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9876000285148621,"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":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7752776145935059},{"id":"https://openalex.org/keywords/listing","display_name":"Listing (finance)","score":0.7726241946220398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7202427983283997},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6514655351638794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5360612869262695},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5286477208137512},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4899653494358063},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47774428129196167},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4740818738937378},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4520558714866638},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2699551582336426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19031399488449097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12426182627677917},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12006774544715881},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09890410304069519}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7752776145935059},{"id":"https://openalex.org/C2779820595","wikidata":"https://www.wikidata.org/wiki/Q798505","display_name":"Listing (finance)","level":2,"score":0.7726241946220398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202427983283997},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6514655351638794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5360612869262695},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5286477208137512},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4899653494358063},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47774428129196167},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4740818738937378},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4520558714866638},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2699551582336426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19031399488449097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12426182627677917},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12006774544715881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09890410304069519},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/grc.2008.4664707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grc.2008.4664707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Granular Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2060314721","https://openalex.org/W2100958137","https://openalex.org/W2121996546"],"related_works":["https://openalex.org/W293204540","https://openalex.org/W4360847453","https://openalex.org/W2795534283","https://openalex.org/W1554695299","https://openalex.org/W4210513147","https://openalex.org/W2127475914","https://openalex.org/W1996337522","https://openalex.org/W1999940705","https://openalex.org/W3091981311","https://openalex.org/W2121996546"],"abstract_inverted_index":{"Nowadays":[0],"most":[1],"search":[2],"engine":[3],"like":[4],"Google,":[5],"Baidu,":[6],"demonstrate":[7],"their":[8],"query":[9],"results":[10],"by":[11],"the":[12,31,54,74],"value":[13],"of":[14,28,33,79,81],"item,":[15],"listing":[16],"them":[17],"in":[18,25],"several":[19,44,63],"pages.":[20],"As":[21],"we":[22,52],"are":[23,62,77],"now":[24],"an":[26,86],"age":[27],"information":[29],"explosion,":[30],"number":[32],"pages":[34],"will":[35,58],"be":[36,59],"huge":[37],"and":[38,70],"users":[39],"have":[40],"to":[41],"glance":[42],"over":[43],"before":[45],"they":[46,49],"get":[47],"what":[48],"want.":[50],"If":[51],"cluster":[53],"results,":[55],"this":[56,83],"problem":[57],"solved.":[60],"There":[61],"clustering":[64],"methods,":[65],"but":[66],"not":[67],"quite":[68],"accurate":[69],"efficient,":[71],"epically":[72],"when":[73],"result":[75],"sets":[76],"consist":[78],"millions":[80],"items.":[82],"article":[84],"describe":[85],"fast":[87],"method":[88],"under":[89],"Pareto\u2019s":[90],"Principle.":[91]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}