{"id":"https://openalex.org/W180731010","doi":null,"title":"Data Cleaning Methods","display_name":"Data Cleaning Methods","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W180731010","mag":"180731010"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.2066","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csaa.byu.edu/kdd03-papers/winkler.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"William Winkler","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"William Winkler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.02,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89730424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/data-cleaning","display_name":"data cleaning","score":0.9200000166893005},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.7839999794960022},{"id":"https://openalex.org/keywords/fellegi-sunter-model","display_name":"Fellegi-Sunter model","score":0.9819999933242798},{"id":"https://openalex.org/keywords/duplicate-detection","display_name":"duplicate detection","score":0.9039999842643738},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.7570000290870667},{"id":"https://openalex.org/keywords/string-comparison","display_name":"string comparison","score":0.7170000076293945},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.9539999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6555328965187073},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6303002834320068},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.55843186378479},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.4486154615879059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446730375289917},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.18092647194862366},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.10518771409988403},{"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":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.2066","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csaa.byu.edu/kdd03-papers/winkler.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W111418871","https://openalex.org/W1487588218","https://openalex.org/W1554944419","https://openalex.org/W1673955757","https://openalex.org/W1907304379","https://openalex.org/W1975723136","https://openalex.org/W2000484009","https://openalex.org/W2029873015","https://openalex.org/W2034163998","https://openalex.org/W2039548409","https://openalex.org/W2049633694","https://openalex.org/W2049855118","https://openalex.org/W2052390074","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2097089247","https://openalex.org/W2110111529","https://openalex.org/W2117853077","https://openalex.org/W2141634619","https://openalex.org/W2143683307","https://openalex.org/W2160842254","https://openalex.org/W2161600801"],"related_works":["https://openalex.org/W2161600801","https://openalex.org/W4241107823","https://openalex.org/W1796875097","https://openalex.org/W1482865806","https://openalex.org/W2053062910","https://openalex.org/W36024057","https://openalex.org/W3115636677","https://openalex.org/W2072510577","https://openalex.org/W7042834144","https://openalex.org/W2769740009"],"abstract_inverted_index":{"Data":[0],"Cleaning":[1],"methods":[2,40],"are":[3],"used":[4],"for":[5,41],"finding":[6],"duplicates":[7],"within":[8],"a":[9],"file":[10],"or":[11],"across":[12],"sets":[13],"of":[14,24],"files.":[15],"This":[16],"overview":[17],"provides":[18,30],"background":[19],"on":[20],"the":[21],"Fellegi-Sunter":[22,28],"model":[23,29],"record":[25],"linkage.":[26],"The":[27],"an":[31],"optimal":[32,44],"theoretical":[33],"classification":[34],"rule.":[35],"Fellegi":[36],"and":[37],"Sunter":[38],"introduced":[39],"automatically":[42],"estimating":[43],"parameters":[45],"without":[46],"training":[47],"data":[48],"that":[49],"we":[50],"extend":[51],"to":[52],"many":[53],"real":[54],"world":[55],"situations.":[56],"Keywords":[57],"EM":[58],"Algorithm,":[59],"string":[60],"comparator,":[61],"unsupervised":[62],"learning.":[63],"1.":[64]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-27T00:00:00"}
