{"id":"https://openalex.org/W2396493611","doi":"https://doi.org/10.3233/978-1-61499-512-8-227","title":"A new approach for cleansing geographical dataset using Levenshtein distance, prior knowledge and contextual information","display_name":"A new approach for cleansing geographical dataset using Levenshtein distance, prior knowledge and contextual information","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2396493611","doi":"https://doi.org/10.3233/978-1-61499-512-8-227","mag":"2396493611","pmid":"https://pubmed.ncbi.nlm.nih.gov/25991137"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-512-8-227","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-512-8-227","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"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/A5079647803","display_name":"Adrien Ugon","orcid":"https://orcid.org/0000-0001-8258-5759"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4389425324","display_name":"Laboratoire d'Informatique M\u00e9dicale et d'Ing\u00e9nierie des Connaissances en e-Sant\u00e9","ror":"https://ror.org/01jr1v359","country_code":null,"type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4389425324"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ugon Adrien","raw_affiliation_strings":["INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4210091437","https://openalex.org/I4389425324"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nicolas Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4389425324","display_name":"Laboratoire d'Informatique M\u00e9dicale et d'Ing\u00e9nierie des Connaissances en e-Sant\u00e9","ror":"https://ror.org/01jr1v359","country_code":null,"type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4389425324"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Thomas","raw_affiliation_strings":["INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4210091437","https://openalex.org/I4389425324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028428393","display_name":"Marion Richard","orcid":"https://orcid.org/0000-0003-0175-2637"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4389425324","display_name":"Laboratoire d'Informatique M\u00e9dicale et d'Ing\u00e9nierie des Connaissances en e-Sant\u00e9","ror":"https://ror.org/01jr1v359","country_code":null,"type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4389425324"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Richard Marion","raw_affiliation_strings":["INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4210091437","https://openalex.org/I4389425324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034385260","display_name":"Patrick M. Gu\u00e9rin","orcid":"https://orcid.org/0000-0002-2257-5097"},"institutions":[{"id":"https://openalex.org/I3018756631","display_name":"Institut des Mondes Africains","ror":"https://ror.org/02qprbz18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I159885104","https://openalex.org/I21491767","https://openalex.org/I2746051580","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I3018756631","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220","https://openalex.org/I51101395","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guerin Patrick","raw_affiliation_strings":["IRSAN, 37 rue des Mathurins, F-75008, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRSAN, 37 rue des Mathurins, F-75008, Paris, France","institution_ids":["https://openalex.org/I3018756631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023974057","display_name":"Pascal Chansard","orcid":null},"institutions":[{"id":"https://openalex.org/I3018756631","display_name":"Institut des Mondes Africains","ror":"https://ror.org/02qprbz18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I159885104","https://openalex.org/I21491767","https://openalex.org/I2746051580","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I3018756631","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220","https://openalex.org/I51101395","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chansard Pascal","raw_affiliation_strings":["IRSAN, 37 rue des Mathurins, F-75008, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRSAN, 37 rue des Mathurins, F-75008, Paris, France","institution_ids":["https://openalex.org/I3018756631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052295173","display_name":"Christophe Demoor","orcid":null},"institutions":[{"id":"https://openalex.org/I3018756631","display_name":"Institut des Mondes Africains","ror":"https://ror.org/02qprbz18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I159885104","https://openalex.org/I21491767","https://openalex.org/I2746051580","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I3018756631","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220","https://openalex.org/I51101395","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Demoor Christophe","raw_affiliation_strings":["IRSAN, 37 rue des Mathurins, F-75008, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRSAN, 37 rue des Mathurins, F-75008, Paris, France","institution_ids":["https://openalex.org/I3018756631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045108626","display_name":"Laurent Toubiana","orcid":"https://orcid.org/0000-0002-1849-9829"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4389425324","display_name":"Laboratoire d'Informatique M\u00e9dicale et d'Ing\u00e9nierie des Connaissances en e-Sant\u00e9","ror":"https://ror.org/01jr1v359","country_code":null,"type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4389425324"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Toubiana Laurent","raw_affiliation_strings":["INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM, U1142, LIMICS, F-75006, Paris, France; Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR_S 1142, LIMICS, F-75006, Paris, France; Universit\u00e9 Paris 13, Sorbonne Paris Cit\u00e9, LIMICS, (UMR_S 1142), F-93430, Villetaneuse, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210091279","https://openalex.org/I4210091437","https://openalex.org/I4389425324"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26340457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"210","issue":null,"first_page":"227","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9089000225067139,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.7716212272644043},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7659322023391724},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.6338685154914856},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.604831874370575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6017364263534546},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5635862350463867},{"id":"https://openalex.org/keywords/concordance","display_name":"Concordance","score":0.5110224485397339},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5065339803695679},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.5026793479919434},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44799911975860596},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.440228134393692},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4134019911289215},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4066677689552307},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.34629666805267334},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.22128444910049438},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.17386659979820251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16985169053077698},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.11177095770835876},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07868203520774841}],"concepts":[{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.7716212272644043},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7659322023391724},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.6338685154914856},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.604831874370575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017364263534546},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5635862350463867},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.5110224485397339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5065339803695679},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5026793479919434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44799911975860596},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.440228134393692},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4134019911289215},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4066677689552307},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.34629666805267334},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.22128444910049438},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.17386659979820251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16985169053077698},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.11177095770835876},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07868203520774841},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005602","descriptor_name":"France","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005602","descriptor_name":"France","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005602","descriptor_name":"France","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019371","descriptor_name":"Topography, Medical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019371","descriptor_name":"Topography, Medical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019371","descriptor_name":"Topography, Medical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-512-8-227","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-512-8-227","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:25991137","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25991137","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W962911587","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W4200551113","https://openalex.org/W2319837024","https://openalex.org/W2343500026","https://openalex.org/W4304208754","https://openalex.org/W2396493611"],"abstract_inverted_index":{"Epidemiological":[0],"studies":[1],"are":[2,80,91,162],"necessary":[3],"to":[4,57,64,110,117,133,145,152],"take":[5],"public":[6],"health":[7],"decisions.":[8],"Their":[9],"relevance":[10],"depends":[11],"on":[12,41,182],"the":[13,44,103,106,112,143,149,160,166,178,194],"quality":[14],"of":[15,25,102,157,185,191],"data.":[16,76],"Doctors":[17],"in":[18,82,96],"continuous":[19],"care":[20],"collect":[21],"a":[22,59,131,154,183],"big":[23],"amount":[24],"data":[26,36],"that":[27,171,202],"can":[28,69],"be":[29,38,70],"used":[30],"for":[31],"epidemiological":[32,124],"purpose,":[33],"but":[34],"spatial":[35,120],"may":[37],"dirty;":[39],"based":[40],"city":[42,60,89,107,113],"names,":[43],"localization":[45],"is":[46,52,63],"imprecise,":[47],"even":[48],"more":[49],"if":[50],"it":[51,172],"misspelled.":[53],"The":[54,99],"only":[55,174],"way":[56],"identify":[58],"without":[61],"ambiguity":[62],"use":[65,148],"its":[66],"identifier,":[67],"which":[68,176],"retrieved":[71],"by":[72,93,164],"cleansing":[73],"geographical":[74],"textual":[75],"In":[77,126],"France,":[78],"cities":[79,95],"organized":[81],"administrative":[83],"zones":[84],"called":[85],"departments":[86],"and":[87,105,116],"some":[88,119],"names":[90],"shared":[92],"several":[94,97,138],"departments.":[98],"clear":[100],"identification":[101],"department":[104],"name":[108],"allows":[109],"deduce":[111],"unique":[114],"identifier":[115],"make":[118],"analysis":[121],"such":[122,135],"as":[123],"studies.":[125],"this":[127],"paper,":[128],"we":[129,147,188],"propose":[130],"method":[132,204],"cleanse":[134],"data,":[136],"using":[137],"steps.":[139],"After":[140],"having":[141],"standardized":[142],"text":[144],"cleanse,":[146],"Levenshtein":[150,196],"distance":[151,197],"generate":[153],"first":[155],"set":[156],"propositions.":[158],"Finally,":[159],"propositions":[161],"filtered,":[163],"removing":[165],"less":[167],"likely":[168],"candidates,":[169],"so":[170],"remains":[173],"one,":[175],"becomes":[177],"chosen":[179],"city.":[180],"Tested":[181],"dataset":[184],"9818":[186],"entries,":[187],"obtained":[189,198],"89.1%":[190],"concordance,":[192],"whereas":[193],"standard":[195],"70.5%.":[199],"This":[200],"demonstrates":[201],"our":[203],"has":[205],"better":[206],"results.":[207]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}