{"id":"https://openalex.org/W1762166282","doi":"https://doi.org/10.1177/0165551509105195","title":"Automated document metadata extraction","display_name":"Automated document metadata extraction","publication_year":2009,"publication_date":"2009-06-11","ids":{"openalex":"https://openalex.org/W1762166282","doi":"https://doi.org/10.1177/0165551509105195","mag":"1762166282"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551509105195","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5023316830","display_name":"Bolanle Adefowoke Ojokoh","orcid":"https://orcid.org/0000-0002-4995-6025"},"institutions":[{"id":"https://openalex.org/I180664298","display_name":"Federal University of Technology","ror":"https://ror.org/01pvx8v81","country_code":"NG","type":"funder","lineage":["https://openalex.org/I180664298"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Bolanle Adefowoke Ojokoh","raw_affiliation_strings":["Department of Computer Science, Federal University of Technology, Nigeria,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Technology, Nigeria,","institution_ids":["https://openalex.org/I180664298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047427901","display_name":"Olumide Sunday Adewale","orcid":"https://orcid.org/0000-0003-4642-0150"},"institutions":[{"id":"https://openalex.org/I180664298","display_name":"Federal University of Technology","ror":"https://ror.org/01pvx8v81","country_code":"NG","type":"funder","lineage":["https://openalex.org/I180664298"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Olumide Sunday Adewale","raw_affiliation_strings":["Department of Computer Science, Federal University of Technology, Nigeria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Technology, Nigeria","institution_ids":["https://openalex.org/I180664298"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112508338","display_name":"Samuel Oluwole Falaki","orcid":null},"institutions":[{"id":"https://openalex.org/I180664298","display_name":"Federal University of Technology","ror":"https://ror.org/01pvx8v81","country_code":"NG","type":"funder","lineage":["https://openalex.org/I180664298"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Samuel Oluwole Falaki","raw_affiliation_strings":["Department of Computer Science, Federal University of Technology, Nigeria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Technology, Nigeria","institution_ids":["https://openalex.org/I180664298"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.04,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":9,"citation_normalized_percentile":{"value":0.955298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":"35","issue":"5","first_page":"563","last_page":"570"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9992,"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":0.9992,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9964,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.989,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.874282},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.844067},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.68183684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5911006},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5446337},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48761168},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45444995},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.42793128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34963033},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29544687},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551509105195","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.72}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":18,"referenced_works":["https://openalex.org/W1504413257","https://openalex.org/W1534730506","https://openalex.org/W1568339100","https://openalex.org/W1575936579","https://openalex.org/W1998839545","https://openalex.org/W2043928274","https://openalex.org/W2072326204","https://openalex.org/W2080928448","https://openalex.org/W2124303864","https://openalex.org/W2140479099","https://openalex.org/W2150721933","https://openalex.org/W2158755884","https://openalex.org/W4237452273","https://openalex.org/W4243220130","https://openalex.org/W4253723135","https://openalex.org/W4255963275","https://openalex.org/W4285719527","https://openalex.org/W4299626704"],"related_works":["https://openalex.org/W2757101400","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2392768766","https://openalex.org/W2362196274","https://openalex.org/W2240384024","https://openalex.org/W2058118494","https://openalex.org/W2004087619","https://openalex.org/W1990527953","https://openalex.org/W1982302668"],"abstract_inverted_index":{"Web":[0],"documents":[1,53],"are":[2],"available":[3],"in":[4,105],"various":[5],"forms,":[6],"most":[7],"of":[8,58,85,95],"which":[9,27],"do":[10],"not":[11],"carry":[12],"additional":[13],"semantics.":[14],"This":[15],"paper":[16],"presents":[17],"a":[18],"model":[19,78],"for":[20,82,89,108],"general":[21],"document":[22],"metadata":[23,86],"extraction.":[24],"The":[25,44,73],"model,":[26],"combines":[28],"segmentation":[29],"by":[30],"keywords":[31],"and":[32,42,71,91],"pattern":[33],"matching":[34],"techniques,":[35],"was":[36,46,61],"implemented":[37],"using":[38,63],"PHP,":[39],"MySQL,":[40],"JavaScript":[41],"HTML.":[43],"system":[45,60],"tested":[47],"with":[48,98],"40":[49],"randomly":[50],"selected":[51],"PDF":[52],"(mainly":[54],"theses).":[55],"An":[56],"evaluation":[57],"the":[59,77,83,106],"done":[62],"standard":[64],"criteria":[65],"measures":[66],"namely":[67],"precision,":[68],"recall,":[69],"accuracy":[70],"F-measure.":[72],"results":[74],"show":[75],"that":[76],"is":[79],"relatively":[80],"effective":[81],"task":[84],"extraction,":[87],"especially":[88],"theses":[90],"dissertations.":[92],"A":[93],"combination":[94],"machine":[96],"learning":[97],"these":[99],"rule-based":[100],"methods":[101],"will":[102],"be":[103],"explored":[104],"future":[107],"better":[109],"results.":[110]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1762166282","counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-04-16T00:53:55.023266","created_date":"2016-06-24"}