{"id":"https://openalex.org/W2055405704","doi":"https://doi.org/10.1145/1008694.1008697","title":"Iterative record linkage for cleaning and integration","display_name":"Iterative record linkage for cleaning and integration","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2055405704","doi":"https://doi.org/10.1145/1008694.1008697","mag":"2055405704"},"language":"en","primary_location":{"id":"doi:10.1145/1008694.1008697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","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/A5101727281","display_name":"Indrajit Bhattacharya","orcid":"https://orcid.org/0009-0004-4279-538X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indrajit Bhattacharya","raw_affiliation_strings":["University of Maryland, College Park, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086169451","display_name":"Lise Getoor","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["University of Maryland, College Park, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.8051,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":{"value":0.9972615,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"18"},"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":0.9728000164031982,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9462000131607056,"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/linkage","display_name":"Linkage (software)","score":0.6531856656074524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6167498826980591},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5315962433815002},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06782466173171997}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6531856656074524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6167498826980591},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5315962433815002},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06782466173171997},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1008694.1008697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.7894","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.7894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~getoor/Publications/dmkd04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.1069","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.1069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~indrajit/DOCS/dmkd04.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":33,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W41404523","https://openalex.org/W46452414","https://openalex.org/W1484228408","https://openalex.org/W1503428008","https://openalex.org/W1523728576","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1581262234","https://openalex.org/W1646278814","https://openalex.org/W2001496424","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2052390074","https://openalex.org/W2052581258","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2102443632","https://openalex.org/W2105423800","https://openalex.org/W2150698190","https://openalex.org/W2154785834","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2164456230","https://openalex.org/W2168190036","https://openalex.org/W2170902582","https://openalex.org/W2603514790","https://openalex.org/W2914002020","https://openalex.org/W2999905431","https://openalex.org/W4285719527","https://openalex.org/W6631230762","https://openalex.org/W6633667658","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/W1501601012","https://openalex.org/W3088855600","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W2178148352","https://openalex.org/W1936317645"],"abstract_inverted_index":{"Record":[0],"linkage,":[1],"the":[2,11,74,90,93,96,137,158],"problem":[3],"of":[4,71,92,162,165],"determining":[5],"when":[6,168],"two":[7],"records":[8],"refer":[9],"to":[10,49,99,124,132,149],"same":[12],"entity,":[13],"has":[14],"applications":[15],"for":[16,22],"both":[17],"data":[18,24],"cleaning":[19],"(deduplication)":[20],"and":[21,160],"integrating":[23],"from":[25],"multiple":[26,134],"sources.":[27],"Traditional":[28],"approaches":[29],"use":[30,164],"a":[31,44,68,109,120],"similarity":[32,41],"measure":[33],"that":[34,156],"compares":[35],"tuples'":[36],"attribute":[37],"values;":[38],"tuples":[39,98],"with":[40,108],"scores":[42],"above":[43],"certain":[45],"threshold":[46],"are":[47,141],"declared":[48],"be":[50],"matches.":[51],"While":[52],"this":[53,115],"method":[54],"can":[55,105],"perform":[56],"quite":[57],"well":[58],"in":[59,73,76,145],"many":[60],"domains,":[61],"particularly":[62],"domains":[63,78],"where":[64],"there":[65],"is":[66,84,102],"not":[67,85],"large":[69],"amount":[70],"noise":[72],"data,":[75],"some":[77],"looking":[79],"only":[80],"at":[81,119],"tuple":[82],"values":[83],"enough.":[86],"By":[87],"also":[88],"examining":[89],"context":[91],"tuple,":[94],"i.e.":[95],"other":[97],"which":[100],"it":[101],"linked,":[103],"we":[104,129],"come":[106],"up":[107],"more":[110],"accurate":[111],"linkage":[112],"decision.":[113],"But":[114],"additional":[116,151],"accuracy":[117],"comes":[118],"price.":[121],"In":[122],"order":[123],"correctly":[125],"find":[126],"all":[127],"duplicates,":[128],"may":[130,144],"need":[131],"make":[133],"passes":[135],"over":[136],"data;":[138],"as":[139],"linkages":[140],"discovered,":[142],"they":[143],"turn":[146],"allow":[147],"us":[148],"discover":[150],"linkages.":[152],"We":[153],"present":[154],"results":[155],"illustrate":[157],"power":[159],"feasibility":[161],"making":[163],"join":[166],"information":[167],"comparing":[169],"records.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}