{"id":"https://openalex.org/W2166988329","doi":"https://doi.org/10.1145/1255175.1255213","title":"Adaptive sorted neighborhood methods for efficient record linkage","display_name":"Adaptive sorted neighborhood methods for efficient record linkage","publication_year":2007,"publication_date":"2007-06-18","ids":{"openalex":"https://openalex.org/W2166988329","doi":"https://doi.org/10.1145/1255175.1255213","mag":"2166988329"},"language":"en","primary_location":{"id":"doi:10.1145/1255175.1255213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008987451","display_name":"Yan Su","orcid":"https://orcid.org/0000-0002-1546-2799"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Su Yan","raw_affiliation_strings":["Penn. State University, State College, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn. State University, State College, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["Penn. State University, State College, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn. State University, State College, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee C. Giles","raw_affiliation_strings":["Penn. State University, State College, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn. State University, State College, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7732,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.94574341,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"194"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9135000109672546,"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/record-linkage","display_name":"Record linkage","score":0.7798846960067749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711488008499146},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.5978112816810608},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5453358292579651},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.5424490571022034},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5409224629402161},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5393445491790771},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.49368104338645935},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4151880443096161},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.2968198359012604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1763458549976349},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07416972517967224}],"concepts":[{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.7798846960067749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711488008499146},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5978112816810608},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5453358292579651},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.5424490571022034},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5409224629402161},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5393445491790771},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.49368104338645935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4151880443096161},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2968198359012604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1763458549976349},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07416972517967224},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1255175.1255213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/40504","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/40504","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.2378","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.2378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nike.psu.edu/publications/jcdl07-adaptive.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W154872207","https://openalex.org/W1506138338","https://openalex.org/W1540269031","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1646278814","https://openalex.org/W1991885012","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2105423800","https://openalex.org/W2111116800","https://openalex.org/W2116544254","https://openalex.org/W2116690618","https://openalex.org/W2128661986","https://openalex.org/W2135223301","https://openalex.org/W2141634619","https://openalex.org/W2154498027","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2171574281","https://openalex.org/W2999905431","https://openalex.org/W4214588406","https://openalex.org/W6632038546","https://openalex.org/W6683373780"],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W4280518517","https://openalex.org/W3111878056","https://openalex.org/W3211905090","https://openalex.org/W1936317645","https://openalex.org/W4310568775"],"abstract_inverted_index":{"Traditionally,":[0],"record":[1,33,116,127],"linkage":[2,34,117,128],"algorithms":[3,35],"have":[4,36,46],"played":[5],"an":[6],"important":[7],"role":[8],"in":[9,22],"maintaining":[10],"digital":[11,26,168],"libraries":[12,169],"-":[13],"i.e.,":[14],"identifying":[15],"matching":[16],"citations":[17],"or":[18,24,75,91],"authors":[19],"for":[20],"consolidation":[21],"updating":[23],"integrating":[25],"libraries.":[27],"As":[28],"such,":[29],"a":[30,47,125],"variety":[31],"of":[32,49,69,85,115,167],"been":[37],"developed":[38],"and":[39,110,135,143,157,163,170],"deployed":[40],"successfully.":[41],"Often,":[42],"however,":[43],"existing":[44,86],"solutions":[45,87],"set":[48,54],"parameters":[50,71,114],"whose":[51],"values":[52,68],"are":[53,59],"by":[55,108,145],"human":[56],"experts":[57],"off-lineand":[58],"fixed":[60,149],"during":[61],"the":[62,66,83,130],"execution.":[63],"Since":[64],"finding":[65],"ideal":[67,79],"such":[70,77,113],"is":[72,93,155],"not":[73],"straightforward,":[74],"no":[76],"single":[78],"value":[80],"even":[81],"exists,":[82],"applicability":[84],"to":[88],"new":[89],"scenarios":[90],"domains":[92],"greatly":[94],"hampered.":[95],"To":[96,119],"remedy":[97],"this":[98],"problem,":[99],"we":[100,123,138],"argue":[101],"that":[102],"one":[103],"can":[104,139],"achieve":[105,140],"significant":[106],"improvement":[107],"adaptively":[109,146],"dynamically":[111],"changing":[112,147],"algorithms.":[118],"validate":[120],"our":[121],"hypothesis,":[122],"take":[124],"classical":[126],"algorithm,":[129],"sorted":[131],"neighborhood":[132],"method":[133],"(SNM),":[134],"demonstrate":[136],"how":[137],"improved":[141],"accuracy":[142],"performance":[144],"its":[148],"sliding":[150],"window":[151],"size.":[152],"Our":[153],"claim":[154],"analytically":[156],"empirically":[158],"validated":[159],"using":[160],"both":[161],"real":[162],"synthetic":[164],"data":[165],"sets":[166],"other":[171],"domains.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}