{"id":"https://openalex.org/W2035615211","doi":"https://doi.org/10.1145/1401890.1401913","title":"Automatic record linkage using seeded nearest neighbour and support vector machine classification","display_name":"Automatic record linkage using seeded nearest neighbour and support vector machine classification","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2035615211","doi":"https://doi.org/10.1145/1401890.1401913","mag":"2035615211"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-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/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":true,"raw_author_name":"Peter Christen","raw_affiliation_strings":["The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022945960"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":10.0735,"has_fulltext":false,"cited_by_count":173,"citation_normalized_percentile":{"value":0.98103711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"159"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9646000266075134,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9541000127792358,"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":0.8088034391403198},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6495428085327148},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.610931396484375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5924922823905945},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5780095458030701},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5625536441802979},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5082530379295349},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.4957776963710785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4754961431026459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46040570735931396},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4273383617401123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08188530802726746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088034391403198},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6495428085327148},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.610931396484375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5924922823905945},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5780095458030701},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5625536441802979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5082530379295349},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.4957776963710785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754961431026459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46040570735931396},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4273383617401123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08188530802726746},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1401890.1401913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.1107","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.1107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.anu.edu.au/~Peter.Christen/publications/kdd2008christen.pdf","raw_type":"text"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/38481","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/38481","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325396","display_name":"NSW Ministry of Health","ror":null},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1518784700","https://openalex.org/W1547087245","https://openalex.org/W1566255553","https://openalex.org/W1582775886","https://openalex.org/W1589277632","https://openalex.org/W1597164057","https://openalex.org/W1646278814","https://openalex.org/W1673955757","https://openalex.org/W2038553416","https://openalex.org/W2064549288","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2101246646","https://openalex.org/W2108991785","https://openalex.org/W2111625757","https://openalex.org/W2113975509","https://openalex.org/W2117148965","https://openalex.org/W2130439782","https://openalex.org/W2143683307","https://openalex.org/W2148019918","https://openalex.org/W2153635508","https://openalex.org/W2154785834","https://openalex.org/W2156748834","https://openalex.org/W2161600801","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W2585105539","https://openalex.org/W3120421331","https://openalex.org/W4205241946","https://openalex.org/W4285719527","https://openalex.org/W6633793231"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W4315815996"],"abstract_inverted_index":{"The":[0,39],"task":[1],"of":[2,13,36,41,57,71,91],"linking":[3,42,62],"databases":[4,64],"is":[5,24,43,65,110],"an":[6,10,124],"important":[7],"step":[8],"in":[9,114],"increasing":[11],"number":[12],"data":[14,19],"mining":[15],"projects,":[16],"because":[17],"linked":[18],"can":[20],"contain":[21],"information":[22],"that":[23,29,50],"not":[25,112],"available":[26,113],"otherwise,":[27],"or":[28,86,118],"would":[30],"require":[31,106],"time-consuming":[32,128],"and":[33,46,68,76,127],"expensive":[34],"collection":[35],"specific":[37],"data.":[38],"aim":[40],"to":[44,52,120],"match":[45],"aggregate":[47],"all":[48],"records":[49],"refer":[51],"the":[53,58,66,92],"same":[54],"entity.":[55],"One":[56],"major":[59],"challenges":[60],"when":[61],"large":[63],"efficient":[67],"accurate":[69],"classification":[70,80,96],"record":[72],"pairs":[73],"into":[74],"matches":[75],"non-matches.":[77],"While":[78],"traditionally":[79],"was":[81],"based":[82,99],"on":[83,87,100],"manually-set":[84],"thresholds":[85],"statistical":[88],"procedures,":[89],"many":[90],"more":[93],"recently":[94],"developed":[95],"methods":[97],"are":[98],"supervised":[101],"learning":[102],"techniques.":[103],"They":[104],"therefore":[105],"training":[107],"data,":[108],"which":[109],"often":[111],"real":[115],"world":[116],"situations":[117],"has":[119],"be":[121],"prepared":[122],"manually,":[123],"expensive,":[125],"cumbersome":[126],"process.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}
