{"id":"https://openalex.org/W2342638730","doi":"https://doi.org/10.1109/jcdl.2003.1204842","title":"Automatic document metadata extraction using support vector machines","display_name":"Automatic document metadata extraction using support vector machines","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2342638730","doi":"https://doi.org/10.1109/jcdl.2003.1204842","mag":"2342638730"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2003.1204842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2003.1204842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Joint Conference on Digital Libraries, 2003. Proceedings.","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":"Hui Han","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Han","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"C.L. Giles","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.L. Giles","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"E. Manavoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Manavoglu","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongyuan Zha","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenyue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyue Zhang","raw_affiliation_strings":["Department of Mathematics, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"E.A. Fox","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E.A. Fox","raw_affiliation_strings":["Department of Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.6157,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90230841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9702000021934509,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9702000021934509,"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":0.7591444849967957},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6621479988098145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.446347177028656},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.43963339924812317},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3994169533252716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3844376504421234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591444849967957},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6621479988098145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.446347177028656},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.43963339924812317},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3994169533252716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3844376504421234},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jcdl.2003.1204842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2003.1204842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Joint Conference on Digital Libraries, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"mag:2342638730","is_oa":false,"landing_page_url":"http://ci.nii.ac.jp/naid/80016038761","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"ACM/IEEE Joint Conference on Digital Libraries","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1485507288","https://openalex.org/W1563088657","https://openalex.org/W1983311927","https://openalex.org/W1993343275","https://openalex.org/W1999595135","https://openalex.org/W2000890209","https://openalex.org/W2034170092","https://openalex.org/W2040909025","https://openalex.org/W2050331639","https://openalex.org/W2063287522","https://openalex.org/W2064580901","https://openalex.org/W2154498027","https://openalex.org/W2162630660","https://openalex.org/W2170654002","https://openalex.org/W4230816203","https://openalex.org/W4235186159","https://openalex.org/W4239696231","https://openalex.org/W6633261560","https://openalex.org/W6634115791","https://openalex.org/W6634328381","https://openalex.org/W6635548358","https://openalex.org/W6636392717","https://openalex.org/W6640267182","https://openalex.org/W6648840710","https://openalex.org/W6682082992","https://openalex.org/W6683373780","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2563583032","https://openalex.org/W2147880316","https://openalex.org/W2526432449","https://openalex.org/W2084604283","https://openalex.org/W3096042468","https://openalex.org/W1995111176","https://openalex.org/W2319795292","https://openalex.org/W3197079476","https://openalex.org/W2783473080","https://openalex.org/W3154170504","https://openalex.org/W2387664080","https://openalex.org/W2383967660","https://openalex.org/W1508368570","https://openalex.org/W3163092115","https://openalex.org/W2110907671","https://openalex.org/W2946570722","https://openalex.org/W2278641021","https://openalex.org/W34731667","https://openalex.org/W145709626","https://openalex.org/W2855285647"],"abstract_inverted_index":{"Automatic":[0],"metadata":[1,21,32,96,130,144,153],"generation":[2],"provides":[3],"scalability":[4],"and":[5,10,18,40,113,122,166],"usability":[6],"for":[7,31],"digital":[8,158,181],"libraries":[9,159],"their":[11],"collections.":[12],"Machine":[13],"learning":[14,47],"methods":[15,48],"offer":[16],"robust":[17],"adaptable":[19],"automatic":[20],"extraction.":[22],"We":[23,109,173],"describe":[24],"a":[25],"support":[26],"vector":[27],"machine":[28,46],"classification-based":[29],"method":[30,54,146],"extraction":[33,97,131,145,154],"from":[34],"header":[35,61],"part":[36],"of":[37,59,66,87,106,115,119,156],"research":[38],"papers":[39],"show":[41],"that":[42,111],"it":[43,175],"outperforms":[44],"other":[45,180],"on":[49],"the":[50,60,78,83,92,102,116,120,129,140,152,157],"same":[51],"task.":[52],"The":[53],"first":[55],"classifies":[56],"each":[57,107],"line":[58,79],"into":[62],"one":[63],"or":[64],"more":[65],"15":[67],"classes.":[68],"An":[69,133],"iterative":[70],"convergence":[71],"procedure":[72],"is":[73,98],"then":[74],"used":[75],"to":[76,150,179],"improve":[77,128,151],"classification":[80,141],"by":[81,100],"using":[82],"predicted":[84],"class":[85],"labels":[86],"its":[88],"neighbor":[89],"lines":[90],"in":[91],"previous":[93],"round.":[94],"Further":[95],"done":[99],"seeking":[101],"best":[103],"chunk":[104],"boundaries":[105],"line.":[108],"found":[110],"discovery":[112],"use":[114],"structural":[117],"patterns":[118],"data":[121],"domain":[123],"based":[124],"word":[125],"clustering":[126],"can":[127,176],"performance.":[132,142],"appropriate":[134],"feature":[135],"normalization":[136],"also":[137],"greatly":[138],"improves":[139],"Our":[143],"was":[147],"originally":[148],"designed":[149],"quality":[155],"Citeseer":[160],"[S.":[161],"Lawrence":[162],"et":[163,170],"al.,":[164,171],"(1999)]":[165],"EbizSearch":[167],"[Y.":[168],"Petinot":[169],"(2003)].":[172],"believe":[174],"be":[177],"generalized":[178],"libraries.":[182]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}