{"id":"https://openalex.org/W3207430861","doi":"https://doi.org/10.1108/ijwis-05-2021-0058","title":"Deep learning based approach to unstructured record linkage","display_name":"Deep learning based approach to unstructured record linkage","publication_year":2021,"publication_date":"2021-10-16","ids":{"openalex":"https://openalex.org/W3207430861","doi":"https://doi.org/10.1108/ijwis-05-2021-0058","mag":"3207430861"},"language":"en","primary_location":{"id":"doi:10.1108/ijwis-05-2021-0058","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijwis-05-2021-0058","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pureadmin.qub.ac.uk/ws/files/273397384/IJWIS_manuscript.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103002181","display_name":"Anna Jurek-Loughrey","orcid":"https://orcid.org/0000-0003-1002-5079"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anna Jurek-Loughrey","raw_affiliation_strings":["Department of Computer Science, Queen\u2019s University Belfast, Belfast, UK","Department of Computer Science, Queen's University Belfast, Belfast, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Queen\u2019s University Belfast, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"Department of Computer Science, Queen's University Belfast, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103002181"],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":0.894,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76701451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":"6","first_page":"607","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9584000110626221,"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/T10028","display_name":"Topic Modeling","score":0.9465000033378601,"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":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8864328861236572},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.7306343913078308},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5641549825668335},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5554456114768982},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5377421975135803},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5337110161781311},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5209746956825256},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5031914114952087},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48514947295188904},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.43674567341804504},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.42869627475738525},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42398756742477417},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4161542057991028},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4136934280395508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079005718231201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8864328861236572},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7306343913078308},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5641549825668335},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5554456114768982},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5377421975135803},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5337110161781311},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5209746956825256},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5031914114952087},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48514947295188904},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.43674567341804504},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.42869627475738525},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42398756742477417},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4161542057991028},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4136934280395508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079005718231201},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1108/ijwis-05-2021-0058","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijwis-05-2021-0058","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/f43fae51-9a00-4843-8904-9966541d9b0c","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/f43fae51-9a00-4843-8904-9966541d9b0c","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/273397384/IJWIS_manuscript.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jurek-Loughrey, A 2021, 'Deep Learning Based Approach to Unstructured Record Linkage', International Journal of Web Information Systems. https://doi.org/10.1108/IJWIS-05-2021-0058","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/f43fae51-9a00-4843-8904-9966541d9b0c","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/f43fae51-9a00-4843-8904-9966541d9b0c","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/273397384/IJWIS_manuscript.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jurek-Loughrey, A 2021, 'Deep Learning Based Approach to Unstructured Record Linkage', International Journal of Web Information Systems. https://doi.org/10.1108/IJWIS-05-2021-0058","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207430861.pdf","grobid_xml":"https://content.openalex.org/works/W3207430861.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W41404523","https://openalex.org/W986840995","https://openalex.org/W1134508972","https://openalex.org/W1647671624","https://openalex.org/W1981590391","https://openalex.org/W1984052055","https://openalex.org/W1985558865","https://openalex.org/W2014964486","https://openalex.org/W2031250218","https://openalex.org/W2034190452","https://openalex.org/W2041439319","https://openalex.org/W2108991785","https://openalex.org/W2114764731","https://openalex.org/W2127589108","https://openalex.org/W2135223301","https://openalex.org/W2250539671","https://openalex.org/W2403575732","https://openalex.org/W2508865106","https://openalex.org/W2615504032","https://openalex.org/W2733471169","https://openalex.org/W2763940251","https://openalex.org/W2788018346","https://openalex.org/W2890732907","https://openalex.org/W2896457183","https://openalex.org/W2978725006","https://openalex.org/W2997181101","https://openalex.org/W3011807731","https://openalex.org/W3091905774","https://openalex.org/W3146259567","https://openalex.org/W3186756857","https://openalex.org/W3207430861"],"related_works":["https://openalex.org/W3014300295","https://openalex.org/W2747121858","https://openalex.org/W1629725936","https://openalex.org/W2365088826","https://openalex.org/W4253934035","https://openalex.org/W2734587838","https://openalex.org/W2397315971","https://openalex.org/W2963260880","https://openalex.org/W3119940851","https://openalex.org/W3207430861"],"abstract_inverted_index":{"Purpose":[0],"In":[1,164],"the":[2,14,26,62,76,97,104,112,128,136,165,170,182,185,194,207,212,225,231,234,251,256,266,296,304,313,320,326,342,345],"world":[3,65],"of":[4,16,28,52,106,111,133,139,150,184,224,233,255,286,319,328,344],"big":[5],"data,":[6],"data":[7,20,44,77,89,121,141,179,288],"integration":[8,78],"technology":[9],"is":[10,49,81,85,153,352],"crucial":[11,73],"for":[12,87,160],"maximising":[13],"capability":[15],"data-driven":[17],"decision-making.":[18],"Integrating":[19],"from":[21,57],"multiple":[22,58],"sources":[23,59,90,122],"drastically":[24],"expands":[25,211],"power":[27],"information":[29],"and":[30,54,69,125,237,350],"allows":[31],"us":[32],"to":[33,39,91,154,176,242,265,340,355],"address":[34,325],"questions":[35],"that":[36,60,117,193,202,250,295],"are":[37,123,145],"impossible":[38],"answer":[40],"using":[41],"a":[42,50,72,93,156,173,308,334],"single":[43],"source.":[45],"Record":[46],"Linkage":[47],"(RL)":[48],"task":[51],"identifying":[53],"linking":[55,177],"records":[56,98,118],"describe":[61],"same":[63,129],"real":[64],"object":[66],"(e.g.":[67],"person),":[68],"it":[70,84,239,291],"plays":[71],"role":[74],"in":[75,263,272,283,317],"process.":[79],"RL":[80,114,158,235],"challenging,":[82],"as":[83],"uncommon":[86],"different":[88,120],"share":[92],"unique":[94],"identifier.":[95],"Hence,":[96],"must":[99],"be":[100],"matched":[101],"based":[102,180,301,338],"on":[103,181,197,302],"comparison":[105,264],"their":[107],"corresponding":[108],"values.":[109],"Most":[110],"existing":[113],"techniques":[115],"assume":[116],"across":[119],"structured":[124],"represented":[126],"by":[127,220],"scheme":[130],"(i.e.":[131],"set":[132],"attributes).":[134],"Given":[135],"increasing":[137],"amount":[138],"heterogeneous":[140],"sources,":[142],"those":[143],"assumptions":[144,205],"rather":[146],"unrealistic.":[147],"The":[148,246],"purpose":[149],"this":[151,331],"paper":[152,210,332],"propose":[155],"novel":[157,174],"model":[159,236,270,314,349],"unstructured":[161,178,329],"data.":[162,208],"Design/methodology/approach":[163],"previous":[166,213],"work":[167,214],"(Jurek-Loughrey,":[168],"2020),":[169],"authors":[171],"proposed":[172,271,298],"approach":[175,339],"application":[183],"Siamese":[186,226,257,267,305,346],"Multilayer":[187,268,309,347],"Perceptron":[188,269,310],"model.":[189],"It":[190],"was":[191],"demonstrated":[192,294],"method":[195],"performed":[196],"par":[198],"with":[199,307],"other":[200],"approaches":[201],"make":[203,351],"constraining":[204],"regarding":[206],"This":[209],"originally":[215],"presented":[216],"at":[217],"iiWAS2020":[218],"[16]":[219],"exploring":[221],"new":[222,252,335],"architectures":[223],"Neural":[227,258],"Network,":[228],"which":[229],"improves":[230],"generalisation":[232,343],"makes":[238,312],"less":[240,353],"sensitive":[241,354],"parameter":[243,321,356],"selection.":[244,322,357],"Findings":[245],"experimental":[247],"results":[248,262,279],"confirm":[249],"Autoencoder-based":[253],"architecture":[254,300],"Network":[259],"obtains":[260],"better":[261],"(Jurek":[273],"et":[274],"al.":[275],",":[276],"2020).":[277],"Better":[278],"have":[280],"been":[281,293],"achieved":[282],"three":[284],"out":[285],"four":[287],"sets.":[289],"Furthermore,":[290],"has":[292],"second":[297],"(hybrid)":[299],"integrating":[303],"Autoencoder":[306],"model,":[311],"more":[315],"stable":[316],"terms":[318],"Originality/value":[323],"To":[324],"problem":[327],"RL,":[330],"presents":[333],"deep":[336],"learning":[337],"improve":[341],"Preceptron":[348]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}