{"id":"https://openalex.org/W2137494120","doi":"https://doi.org/10.1080/713827173","title":"Cooperative strategy for web data mining and cleaning","display_name":"Cooperative strategy for web data mining and cleaning","publication_year":2003,"publication_date":"2003-05-01","ids":{"openalex":"https://openalex.org/W2137494120","doi":"https://doi.org/10.1080/713827173","mag":"2137494120"},"language":"en","primary_location":{"id":"doi:10.1080/713827173","is_oa":true,"landing_page_url":"https://doi.org/10.1080/713827173","pdf_url":"https://www.tandfonline.com/doi/epdf/10.1080/713827173?needAccess=true&role=button","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.tandfonline.com/doi/epdf/10.1080/713827173?needAccess=true&role=button","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100627256","display_name":"Yuefeng Li","orcid":"https://orcid.org/0000-0002-3594-8980"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yuefeng Li","raw_affiliation_strings":["School of Software Engineering and Data Communications , Queensland University of Technology , Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering and Data Communications , Queensland University of Technology , Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438525","display_name":"Chengqi Zhang","orcid":"https://orcid.org/0000-0001-5715-7154"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengqi Zhang","raw_affiliation_strings":["Faculty of Information Technology , University of Technology , Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology , University of Technology , Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100764178","display_name":"Shichao Zhang","orcid":"https://orcid.org/0000-0001-9981-2970"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]},{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU","CN","PK"],"is_corresponding":false,"raw_author_name":"Shichao Zhang","raw_affiliation_strings":["Faculty of Information Technology , University of Technology , Sydney; Australia and Guangxi Normal University , Guilin, China","Faculty of Information Technology , University of Technology , Sydney","Australia and Guangxi Normal University , Guilin, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology , University of Technology , Sydney; Australia and Guangxi Normal University , Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Faculty of Information Technology , University of Technology , Sydney","institution_ids":["https://openalex.org/I114017466","https://openalex.org/I1323252656"]},{"raw_affiliation_string":"Australia and Guangxi Normal University , Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100627256"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":7.1904,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96799179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":"5-6","first_page":"443","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9840999841690063,"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":0.9840999841690063,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9757000207901001,"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/T11719","display_name":"Data Quality and Management","score":0.9539999961853027,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8774389624595642},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5220844149589539},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5011324882507324},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4845639765262604},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.47703880071640015},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.47535866498947144},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4310363531112671},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38373804092407227},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3329120874404907},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2698134481906891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8774389624595642},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5220844149589539},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5011324882507324},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4845639765262604},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.47703880071640015},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.47535866498947144},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4310363531112671},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38373804092407227},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3329120874404907},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2698134481906891},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/713827173","is_oa":true,"landing_page_url":"https://doi.org/10.1080/713827173","pdf_url":"https://www.tandfonline.com/doi/epdf/10.1080/713827173?needAccess=true&role=button","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:eprints.qut.edu.au:7050","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Artificial Intelligence","raw_type":"Contribution to Journal"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/4002","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/4002","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1080/713827173","is_oa":true,"landing_page_url":"https://doi.org/10.1080/713827173","pdf_url":"https://www.tandfonline.com/doi/epdf/10.1080/713827173?needAccess=true&role=button","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2137494120.pdf","grobid_xml":"https://content.openalex.org/works/W2137494120.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2499527417"],"abstract_inverted_index":{"While":[0],"the":[1,16,54,62,76,84,98,109],"Internet":[2],"and":[3,40,114],"World":[4],"Wide":[5],"Web":[6,37,101],"have":[7,106],"put":[8],"a":[9,30,36,64],"huge":[10],"volume":[11],"of":[12,19],"low-quality":[13],"information":[14,21,27,44],"at":[15],"easy":[17],"access":[18],"an":[20,79],"gathering":[22,45],"system,":[23],"filtering":[24],"out":[25],"irrelevant":[26,72],"has":[28],"become":[29],"big":[31],"challenge.":[32],"In":[33],"this":[34],"paper,":[35],"data":[38,55],"mining":[39,85],"cleaning":[41],"strategy":[42,99,111],"for":[43,53,83],"is":[46,51,67,81,93,112],"proposed.":[47],"A":[48],"data-mining":[49],"model":[50,86],"presented":[52,69],"that":[56,108],"come":[57],"from":[58],"multiple":[59],"agents.":[60],"Using":[61],"model,":[63],"data-cleaning":[65,77],"algorithm":[66],"then":[68],"to":[70,88,96],"eliminate":[71],"data.":[73,102],"To":[74],"evaluate":[75,97],"strategy,":[78],"interpretation":[80],"given":[82],"according":[87],"evidence":[89],"theory.":[90],"An":[91],"experiment":[92],"also":[94],"conducted":[95],"using":[100],"The":[103],"experimental":[104],"results":[105],"shown":[107],"proposed":[110],"efficient":[113],"promising.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
