{"id":"https://openalex.org/W2023607075","doi":"https://doi.org/10.1145/1062745.1062891","title":"An experimental study on large-scale web categorization","display_name":"An experimental study on large-scale web categorization","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2023607075","doi":"https://doi.org/10.1145/1062745.1062891","mag":"2023607075"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tie-Yan LIU","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542734","display_name":"Yiming Yang","orcid":"https://orcid.org/0009-0006-3569-0023"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming YANG","raw_affiliation_strings":["Carnegie Mellon University, PA","Carnegie Mellon University PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103181518","display_name":"Hao Wan","orcid":"https://orcid.org/0000-0001-7188-2803"},"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":false,"raw_author_name":"Hao WAN","raw_affiliation_strings":["Tsinghua University, Beijing, P. R. China","TsingHua University, Beijing, P.R. China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077099058","display_name":"Qian Zhou","orcid":"https://orcid.org/0000-0002-2035-2009"},"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":false,"raw_author_name":"Qian ZHOU","raw_affiliation_strings":["Tsinghua University, Beijing, P. R. China","TsingHua University, Beijing, P.R. China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101870054","display_name":"Bin Gao","orcid":"https://orcid.org/0000-0001-9993-1013"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin GAO","raw_affiliation_strings":["Peking University, Beijing, P. R. China","Peking University Beijing P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, P. R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University Beijing P.R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016928764","display_name":"Hua-Jun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hua-Jun ZENG","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088372348","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-4013-3492"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zheng CHEN","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wei-Ying MA","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1106","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962000250816345,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.7455465793609619},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7126391530036926},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6362118721008301},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6305860280990601},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6026933789253235},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5912761688232422},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5788788199424744},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5561246275901794},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5554986000061035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098199248313904},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45700275897979736},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07239732146263123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455465793609619},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7126391530036926},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6362118721008301},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6305860280990601},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6026933789253235},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5912761688232422},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5788788199424744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5561246275901794},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5554986000061035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098199248313904},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45700275897979736},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07239732146263123},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1062745.1062891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05","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":6,"referenced_works":["https://openalex.org/W1979495886","https://openalex.org/W2005422315","https://openalex.org/W2092689128","https://openalex.org/W2103333826","https://openalex.org/W2118020653","https://openalex.org/W2150102617"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2379882851"],"abstract_inverted_index":{"Taxonomies":[0],"of":[1,7,9,44],"the":[2,42,63],"Web":[3],"typically":[4],"have":[5],"hundreds":[6],"thousands":[8],"categories":[10],"and":[11,30,53,76,85],"skewed":[12],"category":[13],"distribution":[14],"over":[15],"documents.":[16],"It":[17],"is":[18],"not":[19],"clear":[20],"whether":[21],"existing":[22],"text":[23],"classification":[24,89],"technologies":[25],"can":[26],"perform":[27],"well":[28],"on":[29],"scale":[31],"up":[32],"to":[33,72],"such":[34],"large-scale":[35,88],"applications.":[36],"To":[37],"understand":[38],"this,":[39],"we":[40,61],"conducted":[41],"evaluation":[43],"several":[45],"representative":[46],"methods":[47],"(Support":[48],"Vector":[49],"Machines,":[50],"k-Nearest":[51],"Neighbor":[52],"Naive":[54],"Bayes)":[55],"with":[56,68],"Yahoo!":[57],"taxonomies.":[58],"In":[59],"particular,":[60],"evaluated":[62],"effectiveness/efficiency":[64],"tradeoff":[65],"in":[66,87],"classifiers":[67],"hierarchical":[69],"setting":[70],"compared":[71],"conventional":[73],"(flat)":[74],"setting,":[75],"tested":[77],"popular":[78],"threshold":[79],"tuning":[80],"strategies":[81],"for":[82],"their":[83],"scalability":[84],"accuracy":[86],"problems.":[90]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}