{"id":"https://openalex.org/W2165419329","doi":"https://doi.org/10.1177/0165551512459923","title":"Duplicate bibliographic record detection with an OCR-converted source of information","display_name":"Duplicate bibliographic record detection with an OCR-converted source of information","publication_year":2012,"publication_date":"2012-10-15","ids":{"openalex":"https://openalex.org/W2165419329","doi":"https://doi.org/10.1177/0165551512459923","mag":"2165419329"},"language":"en","primary_location":{"id":"doi:10.1177/0165551512459923","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551512459923","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_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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5010019965","display_name":"Shoichi Taniguchi","orcid":"https://orcid.org/0000-0002-6103-7902"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shoichi Taniguchi","raw_affiliation_strings":["School of Library and Information Science, Keio University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Library and Information Science, Keio University, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010019965"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.4139,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70495824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"39","issue":"2","first_page":"153","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9959999918937683,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8018944263458252},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6847895979881287},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6441227793693542},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5949918627738953},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5450246334075928},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4996836185455322},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4934195578098297},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4812569320201874},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4658891260623932},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4530094563961029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43001341819763184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34336644411087036},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06494781374931335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018944263458252},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6847895979881287},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6441227793693542},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5949918627738953},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5450246334075928},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4996836185455322},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4934195578098297},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4812569320201874},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4658891260623932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4530094563961029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43001341819763184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34336644411087036},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06494781374931335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551512459923","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551512459923","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_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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W169634138","https://openalex.org/W619639381","https://openalex.org/W1570448133","https://openalex.org/W1969391848","https://openalex.org/W1976546047","https://openalex.org/W1981140395","https://openalex.org/W1985360555","https://openalex.org/W1986269607","https://openalex.org/W1998729874","https://openalex.org/W2021687463","https://openalex.org/W2039229523","https://openalex.org/W2045597604","https://openalex.org/W2047694158","https://openalex.org/W2064004397","https://openalex.org/W2142110756","https://openalex.org/W2149940336","https://openalex.org/W2320768921","https://openalex.org/W3146259567","https://openalex.org/W4245989934","https://openalex.org/W4253935904","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3002261956","https://openalex.org/W4230848040","https://openalex.org/W2123376283","https://openalex.org/W4387327236","https://openalex.org/W2183488467","https://openalex.org/W1990237101","https://openalex.org/W4309907966","https://openalex.org/W4387896287","https://openalex.org/W2187490799","https://openalex.org/W4300172249"],"abstract_inverted_index":{"Duplicate":[0],"record":[1,37,69,85,97,121,151],"detection":[2,18,63,108,152,164,184],"has":[3],"been":[4,21],"an":[5,28,53,72,123],"important":[6],"issue":[7],"in":[8,46],"the":[9,50,57,95,100,139,147,157,172,175],"fields":[10],"of":[11,34,52,59,126,133,149,171,177,180],"data":[12,141],"and":[13,16,44,76,91,99,122,128,165],"records":[14,93],"management":[15],"various":[17],"methods":[19],"have":[20],"proposed.":[22],"A":[23,106],"new":[24],"method,":[25],"which":[26],"uses":[27],"optical":[29],"character":[30],"recognition":[31],"(OCR)-converted":[32],"source":[33,125,179],"information":[35,127,181],"for":[36,55],"matching":[38,114,136,155],"to":[39,112,185],"detect":[40],"duplicates,":[41],"is":[42,65,144,160],"proposed":[43],"examined":[45,161],"this":[47],"paper.":[48],"First,":[49],"design":[51],"experiment":[54,173],"examining":[56],"performance":[58,137,148],"such":[60],"a":[61,120,131,186],"duplicate":[62,92,107,150,183],"method":[64],"discussed.":[66],"The":[67,169],"base":[68,96],"set":[70,98],"with":[71,82],"OCR-converted":[73,124],"title":[74],"page":[75],"its":[77],"verso":[78],"were":[79,103],"prepared":[80],"along":[81],"two":[83],"test":[84,101],"sets":[86,102],"from":[87],"different":[88],"union":[89],"catalogues,":[90],"between":[94,116,119],"manually":[104],"identified.":[105],"system":[109],"was":[110],"developed":[111],"execute":[113],"(1)":[115],"records,":[117],"(2)":[118],"(3)":[129],"using":[130],"combination":[132],"these.":[134],"Second,":[135],"at":[138,156],"individual":[140],"element":[142,158],"level":[143,159],"examined.":[145],"Third,":[146],"based":[153],"on":[154],"through":[162],"rule-based":[163],"machine":[166],"learning-based":[167],"detection.":[168],"results":[170],"show":[174],"usefulness":[176],"incorporating":[178],"into":[182],"certain":[187],"extent.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}