{"id":"https://openalex.org/W3186756857","doi":"https://doi.org/10.1145/3450527","title":"High-Value Token-Blocking: Efficient Blocking Method for Record Linkage","display_name":"High-Value Token-Blocking: Efficient Blocking Method for Record Linkage","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3186756857","doi":"https://doi.org/10.1145/3450527","mag":"3186756857"},"language":"en","primary_location":{"id":"doi:10.1145/3450527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3450527","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","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/244956097/High_Value_Token_Blocking_Efficient_Blocking_for_Unstructured_Record_Linkage.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044425522","display_name":"Kevin O\u2019Hare","orcid":null},"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":false,"raw_author_name":"Kevin O\u2019hare","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, UK","School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","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":false,"raw_author_name":"Anna Jurek-Loughrey","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, UK","School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004994425","display_name":"Cassio P. de Campos","orcid":"https://orcid.org/0000-0001-9130-1287"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cassio De Campos","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6412,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70445595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"17"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9595000147819519,"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":0.8005565404891968},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.746922492980957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5712738037109375},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5468324422836304},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5298216938972473},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5048366189002991},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43497219681739807},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.43471813201904297},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.43464478850364685},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.43113434314727783},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.42855218052864075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24058151245117188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09069707989692688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8005565404891968},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.746922492980957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5712738037109375},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5468324422836304},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5298216938972473},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5048366189002991},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43497219681739807},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.43471813201904297},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.43464478850364685},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.43113434314727783},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.42855218052864075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24058151245117188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09069707989692688},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3450527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3450527","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/9cd6a89c-8e8e-4782-825c-579150d1ba34","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/9cd6a89c-8e8e-4782-825c-579150d1ba34","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/244956097/High_Value_Token_Blocking_Efficient_Blocking_for_Unstructured_Record_Linkage.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":"O'Hare , K , Jurek-Loughrey , A , Pires , C & de Campos , C 2021 , ' High-Value Token-Blocking: Efficient Blocking Method for Record Linkage ' , ACM Transactions on Knowledge Discovery from Data , vol. 16 , no. 2 , 24 . https://doi.org/10.1145/3450527","raw_type":"article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/da25711a-c21a-4156-9983-1cc0a2262dce","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/da25711a-c21a-4156-9983-1cc0a2262dce","pdf_url":"https://pure.tue.nl/ws/files/190182184/3450527.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"O\u2019hare, K, Jurek-Loughrey, A & de Campos, C 2022, 'High-Value Token-Blocking: Efficient Blocking Method for Record Linkage', ACM Transactions on Knowledge Discovery from Data, vol. 16, no. 2, 24. https://doi.org/10.1145/3450527","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.tue.nl:publications/da25711a-c21a-4156-9983-1cc0a2262dce","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85114989206&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"O\u2019hare, K, Jurek-Loughrey, A & de Campos, C 2022, 'High-Value Token-Blocking: Efficient Blocking Method for Record Linkage', ACM Transactions on Knowledge Discovery from Data, vol. 16, no. 2, 24. https://doi.org/10.1145/3450527","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:tue:oai:pure.tue.nl:publications/da25711a-c21a-4156-9983-1cc0a2262dce","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/da25711a-c21a-4156-9983-1cc0a2262dce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Knowledge Discovery from Ddata, 16(2):24. Association for Computing Machinery, Inc","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/9cd6a89c-8e8e-4782-825c-579150d1ba34","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/9cd6a89c-8e8e-4782-825c-579150d1ba34","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/244956097/High_Value_Token_Blocking_Efficient_Blocking_for_Unstructured_Record_Linkage.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":"O'Hare , K , Jurek-Loughrey , A , Pires , C & de Campos , C 2021 , ' High-Value Token-Blocking: Efficient Blocking Method for Record Linkage ' , ACM Transactions on Knowledge Discovery from Data , vol. 16 , no. 2 , 24 . https://doi.org/10.1145/3450527","raw_type":"article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3186756857.pdf","grobid_xml":"https://content.openalex.org/works/W3186756857.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1124123724","https://openalex.org/W1134508972","https://openalex.org/W1612155886","https://openalex.org/W1922373164","https://openalex.org/W1992930793","https://openalex.org/W1997927541","https://openalex.org/W1998600401","https://openalex.org/W2014964486","https://openalex.org/W2036216970","https://openalex.org/W2073539176","https://openalex.org/W2079649893","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2114764731","https://openalex.org/W2152502401","https://openalex.org/W2163616098","https://openalex.org/W2182703380","https://openalex.org/W2399361902","https://openalex.org/W2441805796","https://openalex.org/W2529367823","https://openalex.org/W2535168187","https://openalex.org/W2733471169","https://openalex.org/W2750964846","https://openalex.org/W2794107983","https://openalex.org/W2795151173","https://openalex.org/W2946741276","https://openalex.org/W2957204582","https://openalex.org/W3119940851","https://openalex.org/W4232666159"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2392835431","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W3161390536","https://openalex.org/W1540269031","https://openalex.org/W154872207"],"abstract_inverted_index":{"Data":[0,8],"integration":[1,17],"is":[2,18,102,179],"an":[3],"important":[4],"component":[5],"of":[6,11,32,45,56,66,111,126,134,138,147,150,156,162],"Big":[7],"analytics.":[9],"One":[10],"the":[12,27,46,54,61],"key":[13],"challenges":[14],"in":[15,50,145],"data":[16,80],"record":[19,47],"linkage,":[20],"that":[21,25,76,101,189],"is,":[22],"matching":[23],"records":[24],"represent":[26],"same":[28],"real-world":[29],"entity.":[30],"Because":[31],"computational":[33,151],"costs,":[34],"methods":[35,121,191],"referred":[36],"to":[37,52,181,185,199],"as":[38,42],"blocking":[39,67,100,193],"are":[40],"employed":[41],"a":[43,64,94,108,124,129],"part":[44],"linkage":[48],"pipeline":[49],"order":[51],"reduce":[53],"number":[55],"comparisons":[57],"among":[58],"records.":[59,159],"In":[60],"past":[62],"decade,":[63],"range":[65,125],"techniques":[68],"have":[69],"been":[70],"proposed.":[71],"Real-world":[72],"applications":[73],"require":[74],"approaches":[75],"can":[77],"handle":[78],"heterogeneous":[79],"sources":[81],"and":[82,96,104,122,136,153,158,167],"do":[83],"not":[84,169],"rely":[85],"on":[86,107],"labelled":[87],"data.":[88],"We":[89,116,141],"propose":[90],"high-value":[91],"token-blocking":[92],"(HVTB),":[93],"simple":[95],"efficient":[97],"approach":[98],"for":[99,192],"unsupervised":[103],"schema-agnostic,":[105],"based":[106],"crafted":[109],"use":[110,149],"Term":[112],"Frequency-Inverse":[113],"Document":[114],"Frequency.":[115],"compare":[117],"HVTB":[118,163],"with":[119,175],"multiple":[120],"over":[123],"datasets,":[127],"including":[128],"novel":[130],"unstructured":[131],"dataset":[132],"composed":[133],"titles":[135],"abstracts":[137],"scientific":[139],"papers.":[140],"thoroughly":[142],"discuss":[143],"results":[144],"terms":[146],"accuracy,":[148],"resources,":[152],"different":[154],"characteristics":[155],"datasets":[157],"The":[160],"simplicity":[161],"yields":[164],"fast":[165],"computations":[166],"does":[168],"harm":[170],"its":[171],"accuracy":[172],"when":[173],"compared":[174],"existing":[176],"approaches.":[177],"It":[178],"shown":[180],"be":[182,195],"significantly":[183],"superior":[184],"other":[186],"methods,":[187],"suggesting":[188],"simpler":[190],"should":[194],"considered":[196],"before":[197],"resorting":[198],"more":[200],"sophisticated":[201],"methods.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}