{"id":"https://openalex.org/W2141753567","doi":"https://doi.org/10.1109/cit.2004.1357322","title":"A maximal frequent itemset approach for web document clustering","display_name":"A maximal frequent itemset approach for web document clustering","publication_year":2004,"publication_date":"2004-12-23","ids":{"openalex":"https://openalex.org/W2141753567","doi":"https://doi.org/10.1109/cit.2004.1357322","mag":"2141753567"},"language":"en","primary_location":{"id":"doi:10.1109/cit.2004.1357322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2004.1357322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Fourth International Conference onComputer and Information Technology, 2004. CIT '04.","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":"https://openalex.org/A5102241885","display_name":"Ling Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ling Zhuang","raw_affiliation_strings":["School of Information Technology, Deakin University, Burwood, VIC, Australia","[School of Information Technology, Deakin University, Burwood, VIC, Australia]"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Burwood, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"[School of Information Technology, Deakin University, Burwood, VIC, Australia]","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101756423","display_name":"Honghua Dai","orcid":"https://orcid.org/0000-0001-9899-7029"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Honghua Dai","raw_affiliation_strings":["School of Information Technology, Deakin University, Burwood, VIC, Australia","[School of Information Technology, Deakin University, Burwood, VIC, Australia]"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Burwood, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"[School of Information Technology, Deakin University, Burwood, VIC, Australia]","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102241885"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":4.1628,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94147913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"922","issue":null,"first_page":"970","last_page":"977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9988999962806702,"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":0.9988999962806702,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.996999979019165,"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":0.9961000084877014,"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":0.7628951072692871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554990649223328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5253925919532776},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5140255689620972},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4885152578353882},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.47625041007995605},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46658995747566223},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.45171478390693665},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4198802411556244},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23871392011642456},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12211385369300842}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7628951072692871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554990649223328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5253925919532776},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5140255689620972},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4885152578353882},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.47625041007995605},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46658995747566223},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.45171478390693665},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4198802411556244},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23871392011642456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12211385369300842},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cit.2004.1357322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2004.1357322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Fourth International Conference onComputer and Information Technology, 2004. CIT '04.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.126.7084","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.126.7084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ieeexplore.ieee.org/iel5/9381/29791/01357322.pdf","raw_type":"text"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30005533","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W60856054","https://openalex.org/W190838824","https://openalex.org/W1492327544","https://openalex.org/W1507051419","https://openalex.org/W1530753374","https://openalex.org/W1546703457","https://openalex.org/W1566159240","https://openalex.org/W1611682757","https://openalex.org/W1886218757","https://openalex.org/W2014351296","https://openalex.org/W2073583237","https://openalex.org/W2108560469","https://openalex.org/W2120970098","https://openalex.org/W2138621811","https://openalex.org/W2244550955","https://openalex.org/W2435251607","https://openalex.org/W6602452485","https://openalex.org/W6633750861","https://openalex.org/W6636657728","https://openalex.org/W6678321130","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W1795405792","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971","https://openalex.org/W2083329789","https://openalex.org/W2387982377","https://openalex.org/W2376574812","https://openalex.org/W4322720815"],"abstract_inverted_index":{"To":[0,29],"efficiently":[1],"and":[2,15,58],"yet":[3],"accurately":[4],"cluster":[5],"Web":[6,13,26,42,98,125],"documents":[7],"is":[8,16,45],"of":[9,20,24,41,74,119,122],"great":[10],"interests":[11],"to":[12,63],"users":[14],"a":[17,25,35],"key":[18],"component":[19],"the":[21,39,71,89,107,117],"searching":[22],"accuracy":[23],"search":[27],"engine.":[28],"achieve":[30],"this,":[31],"this":[32],"paper":[33],"introduces":[34],"new":[36],"approach":[37,68,105],"for":[38,88],"clustering":[40,53],"documents,":[43],"which":[44],"called":[46],"maximal":[47],"frequent":[48],"itemset":[49],"(MFI)":[50],"approach.":[51],"Iterative":[52],"algorithms,":[54],"such":[55],"as":[56,85],"K-means":[57,90],"expectation-maximization":[59],"(EM),":[60],"are":[61,83],"sensitive":[62],"their":[64],"initial":[65,86],"conditions.":[66],"MFI":[67,104],"firstly":[69],"locates":[70],"center":[72,80],"points":[73,81,87],"high":[75],"density":[76],"clusters":[77],"precisely.":[78],"These":[79],"then":[82],"used":[84],"algorithm.":[91],"Our":[92],"experimental":[93],"results":[94],"tested":[95],"on":[96],"3":[97],"document":[99,126],"sets":[100],"show":[101],"that":[102],"our":[103],"outperforms":[106],"other":[108],"methods":[109],"we":[110],"compared":[111],"in":[112,116,124],"most":[113],"cases,":[114],"particularly":[115],"case":[118],"large":[120],"number":[121],"categories":[123],"sets.":[127]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}