{"id":"https://openalex.org/W4306317077","doi":"https://doi.org/10.1145/3511808.3557631","title":"Locality Sensitive Hashing with Temporal and Spatial Constraints for Efficient Population Record Linkage","display_name":"Locality Sensitive Hashing with Temporal and Spatial Constraints for Efficient Population Record Linkage","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317077","doi":"https://doi.org/10.1145/3511808.3557631"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557631","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557631","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067500298","display_name":"Charini Nanayakkara","orcid":"https://orcid.org/0000-0002-7603-1845"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Charini Nanayakkara","raw_affiliation_strings":["The Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022945960","display_name":"Peter Christen","orcid":"https://orcid.org/0000-0003-3435-2015"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Christen","raw_affiliation_strings":["The Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067500298"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.2579,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42721016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4354","last_page":"4358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T11478","display_name":"Caching and Content Delivery","score":0.974399983882904,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9674999713897705,"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/hash-function","display_name":"Hash function","score":0.7947027683258057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260922789573669},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.673341691493988},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.610106885433197},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5648109912872314},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5174034833908081},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47256985306739807},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4671473205089569},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4461989402770996},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.42902541160583496},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29006820917129517}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7947027683258057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260922789573669},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.673341691493988},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.610106885433197},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5648109912872314},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5174034833908081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47256985306739807},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4671473205089569},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4461989402770996},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.42902541160583496},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29006820917129517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557631","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557631","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4272082136","display_name":"University of Edinburgh 2022-2026 ADR UK Programme","funder_award_id":"ES/W010321/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G6570992869","display_name":null,"funder_award_id":"ES/W010321/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317077.pdf","grobid_xml":"https://content.openalex.org/works/W4306317077.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1736726159","https://openalex.org/W1996851530","https://openalex.org/W2024386211","https://openalex.org/W2051144536","https://openalex.org/W2097776316","https://openalex.org/W2147717514","https://openalex.org/W2261544779","https://openalex.org/W2399361902","https://openalex.org/W2606460416","https://openalex.org/W2762887147","https://openalex.org/W2788534864","https://openalex.org/W2798649495","https://openalex.org/W2808464929","https://openalex.org/W2931041401","https://openalex.org/W3013103751","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3093671642","https://openalex.org/W3105771849","https://openalex.org/W3123375411","https://openalex.org/W3160031743","https://openalex.org/W3194434488","https://openalex.org/W3202190154","https://openalex.org/W4210754024","https://openalex.org/W4211193898","https://openalex.org/W7074009674"],"related_works":["https://openalex.org/W2734503711","https://openalex.org/W2262209414","https://openalex.org/W2026551508","https://openalex.org/W3091805362","https://openalex.org/W1984958534","https://openalex.org/W2797770018","https://openalex.org/W2010312633","https://openalex.org/W2383263130","https://openalex.org/W1981919843","https://openalex.org/W4210908722"],"abstract_inverted_index":{"Record":[0],"linkage":[1,29,179],"is":[2,24,83],"the":[3,15,36,77,94,103,118,165,176,187,193],"process":[4],"of":[5,38,67,102,122,167,189],"identifying":[6],"which":[7],"records":[8,39],"within":[9],"or":[10],"across":[11],"databases":[12,129],"refer":[13,75],"to":[14,34,40,70,76,92,116,173],"same":[16,78],"entity.":[17],"Min-hash":[18],"based":[19,145],"Locality":[20],"Sensitive":[21],"Hashing":[22],"(LSH)":[23],"commonly":[25],"used":[26],"in":[27,137,192],"record":[28,61,104,143,168],"as":[30],"a":[31,113,190],"blocking":[32,98],"technique":[33],"reduce":[35],"number":[37],"be":[41,182],"compared.":[42],"However,":[43],"when":[44],"applied":[45],"on":[46,146,154],"large":[47,127],"databases,":[48],"min-hash":[49,81,123,150],"LSH":[50,82,124],"can":[51,163,181],"yield":[52],"highly":[53,84],"skewed":[54],"block":[55,147],"size":[56],"distributions":[57],"and":[58,87,90,100,120,133,140,149],"many":[59],"redundant":[60],"pair":[62,105,169],"comparisons,":[63],"where":[64],"only":[65],"few":[66],"those":[68],"correspond":[69],"true":[71],"matches":[72],"(records":[73],"that":[74,160],"entity).":[79],"Furthermore,":[80],"parameter":[85],"sensitive":[86],"requires":[88],"trial":[89],"error":[91],"determine":[93],"optimal":[95],"trade-off":[96],"between":[97],"quality":[99],"efficiency":[101,166],"comparison":[106,170],"step.":[107],"In":[108],"this":[109],"paper,":[110],"we":[111],"present":[112],"novel":[114],"method":[115,162],"improve":[117,164],"scalability":[119],"robustness":[121],"for":[125],"linking":[126],"population":[128],"by":[130,141,171,184,196],"exploiting":[131],"temporal":[132],"spatial":[134],"information":[135],"available":[136],"personal":[138],"data,":[139],"filtering":[142],"pairs":[144],"sizes":[148],"similarity.":[151],"Our":[152],"evaluation":[153],"three":[155],"real-world":[156],"data":[157],"sets":[158],"shows":[159],"our":[161],"75%":[172],"99%,":[174],"whereas":[175],"final":[177],"average":[178,194],"precision":[180],"improved":[183],"28%":[185],"at":[186],"cost":[188],"reduction":[191],"recall":[195],"4%.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}