{"id":"https://openalex.org/W2156772624","doi":"https://doi.org/10.1109/tkde.2004.1264823","title":"Pebl:web page classification without negative examples","display_name":"Pebl:web page classification without negative examples","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2156772624","doi":"https://doi.org/10.1109/tkde.2004.1264823","mag":"2156772624"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2004.1264823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2004.1264823","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5045521125","display_name":"Hwanjo Yu","orcid":"https://orcid.org/0000-0002-7510-0255"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hwanjo Yu","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103750286","display_name":"Jiawei Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.C. Chang","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":11.9078,"has_fulltext":false,"cited_by_count":255,"citation_normalized_percentile":{"value":0.98497165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"70","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9804999828338623,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704300880432129},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7014115452766418},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6936995387077332},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.573134183883667},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5535967350006104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5380982756614685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5220075249671936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203316569328308},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3839031457901001},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0928598940372467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704300880432129},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7014115452766418},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6936995387077332},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.573134183883667},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5535967350006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5380982756614685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5220075249671936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203316569328308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3839031457901001},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0928598940372467}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2004.1264823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2004.1264823","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.561","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/~hanj/pdf/tkde04_pebl.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.470.7429","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.470.7429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gkmc.utah.edu/7910F/papers/IEEE TKDE web page classification.pdf","raw_type":"text"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/28744","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/28744","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W126367074","https://openalex.org/W1497303847","https://openalex.org/W1538189649","https://openalex.org/W1564518192","https://openalex.org/W1569293908","https://openalex.org/W1588401315","https://openalex.org/W1636292238","https://openalex.org/W1811046429","https://openalex.org/W1861993554","https://openalex.org/W1995482120","https://openalex.org/W2005422315","https://openalex.org/W2028514612","https://openalex.org/W2038553416","https://openalex.org/W2049633694","https://openalex.org/W2063862666","https://openalex.org/W2097089247","https://openalex.org/W2100294832","https://openalex.org/W2105497548","https://openalex.org/W2107008379","https://openalex.org/W2110224739","https://openalex.org/W2115219969","https://openalex.org/W2119821739","https://openalex.org/W2130652100","https://openalex.org/W2131904035","https://openalex.org/W2134222424","https://openalex.org/W2149684865","https://openalex.org/W2153477625","https://openalex.org/W2157886637","https://openalex.org/W2166222296","https://openalex.org/W2167044614","https://openalex.org/W2167075392","https://openalex.org/W4239510810","https://openalex.org/W4243150419","https://openalex.org/W4285719527","https://openalex.org/W6605181927","https://openalex.org/W6629564233","https://openalex.org/W6634137187","https://openalex.org/W6635310694","https://openalex.org/W6636863064","https://openalex.org/W6639315830","https://openalex.org/W6676132248","https://openalex.org/W6679539681","https://openalex.org/W6684391652"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W2397288865"],"abstract_inverted_index":{"Web":[0,10,14,100],"page":[1,101],"classification":[2,102,127],"is":[3,20,251],"one":[4,57],"of":[5,16,25,63,70,138,173,200,213,240],"the":[6,22,27,105,152,159,162,179,182,198,204,210,214,218,223,237,243,256],"essential":[7],"techniques":[8],"for":[9,33,99,107],"mining":[11,26],"because":[12],"classifying":[13],"pages":[15],"an":[17,34,119,170,187],"interesting":[18,35],"class":[19,36,205,216],"often":[21],"first":[23],"step":[24],"Web.":[28],"However,":[29],"constructing":[30],"a":[31,54,61,68,91,139,165],"classifier":[32,167,189],"requires":[37,80],"laborious":[38],"preprocessing":[39],"such":[40],"as":[41,134,136,253,255],"collecting":[42,76,109],"positive":[43,94,130,143,215,241],"and":[44,67,83,131,144,155,229,249],"negative":[45,77,110,145,175,201],"training":[46,78,111],"examples.":[47],"For":[48],"instance,":[49],"in":[50,113,149,217],"order":[51],"to":[52,59,85,124,195,209],"construct":[53],"\"homepage\"":[55],"classifier,":[56],"needs":[58],"collect":[60],"sample":[62,69],"homepages":[64],"(positive":[65],"examples)":[66],"nonhomepages":[71],"(negative":[72],"examples).":[73],"In":[74,158],"particular,":[75],"examples":[79,112],"arduous":[81],"work":[82],"caution":[84],"avoid":[86],"bias.":[87],"The":[88,115],"paper":[89],"presents":[90],"framework,":[92],"called":[93,121],"example":[95],"based":[96],"learning":[97],"(PEBL),":[98],"which":[103,192],"eliminates":[104],"need":[106],"manually":[108],"preprocessing.":[114],"PEBL":[116],"framework":[117],"applies":[118],"algorithm,":[120],"mapping-convergence":[122],"(M-C),":[123],"achieve":[125],"high":[126,135],"accuracy":[128],"(with":[129,142],"unlabeled":[132],"data)":[133],"that":[137,168],"traditional":[140,257],"SVM":[141],"data).":[146],"M-C":[147,224,244],"runs":[148,186],"two":[150],"stages:":[151],"mapping":[153,160],"stage":[154,184],"convergence":[156,183],"stage.":[157],"stage,":[161],"algorithm":[163,225,245],"uses":[164],"weak":[166],"draws":[169],"initial":[171,180],"approximation":[172,199],"\"strong\"":[174],"data.":[176,202],"Based":[177],"on":[178],"approximation,":[181],"iteratively":[185],"internal":[188],"(e.g.,":[190],"SVM)":[191],"maximizes":[193],"margins":[194],"progressively":[196],"improve":[197],"Thus,":[203],"boundary":[206,212],"eventually":[207],"converges":[208],"true":[211],"feature":[219],"space.":[220],"We":[221],"present":[222],"with":[226],"supporting":[227],"theoretical":[228],"experimental":[230],"justifications.":[231],"Our":[232],"experiments":[233],"show":[234],"that,":[235],"given":[236],"same":[238],"set":[239],"examples;":[242],"outperforms":[246],"one-class":[247],"SVMs,":[248],"it":[250],"almost":[252],"accurate":[254],"SVMs.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":18}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
