{"id":"https://openalex.org/W2783833019","doi":"https://doi.org/10.1109/bigdata.2017.8258223","title":"Improving data quality through high precision gender categorization","display_name":"Improving data quality through high precision gender categorization","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783833019","doi":"https://doi.org/10.1109/bigdata.2017.8258223","mag":"2783833019"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","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/A5077753479","display_name":"Daniel B. M\u00fcller","orcid":"https://orcid.org/0000-0001-7747-9011"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Daniel Muller","raw_affiliation_strings":["Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036764888","display_name":"Yiea-Funk Te","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yiea-Funk Te","raw_affiliation_strings":["Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108294657","display_name":"Pratiksha Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pratiksha Jain","raw_affiliation_strings":["Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Management, Technology and Economics ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077753479"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.5167,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7317691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"2628","last_page":"2636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9822999835014343,"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/T13546","display_name":"Census and Population Estimation","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7733093500137329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557862997055054},{"id":"https://openalex.org/keywords/nationality","display_name":"Nationality","score":0.7266904711723328},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.57383793592453},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5421510934829712},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5030350089073181},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49889135360717773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44011980295181274},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4396131932735443},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43842920660972595},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4161449372768402},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3861483931541443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3620191216468811},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1277901828289032},{"id":"https://openalex.org/keywords/immigration","display_name":"Immigration","score":0.10271745920181274},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08698827028274536}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7733093500137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557862997055054},{"id":"https://openalex.org/C2777138209","wikidata":"https://www.wikidata.org/wiki/Q231002","display_name":"Nationality","level":3,"score":0.7266904711723328},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.57383793592453},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5421510934829712},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5030350089073181},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49889135360717773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44011980295181274},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4396131932735443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43842920660972595},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4161449372768402},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3861483931541443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3620191216468811},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1277901828289032},{"id":"https://openalex.org/C70036468","wikidata":"https://www.wikidata.org/wiki/Q131288","display_name":"Immigration","level":2,"score":0.10271745920181274},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08698827028274536},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W114869232","https://openalex.org/W848001356","https://openalex.org/W935072310","https://openalex.org/W1612366852","https://openalex.org/W1639095822","https://openalex.org/W1966188439","https://openalex.org/W1975322779","https://openalex.org/W1980241046","https://openalex.org/W1985449126","https://openalex.org/W1996946172","https://openalex.org/W2003030692","https://openalex.org/W2007607666","https://openalex.org/W2015203891","https://openalex.org/W2028566258","https://openalex.org/W2028763616","https://openalex.org/W2040032582","https://openalex.org/W2040792585","https://openalex.org/W2089966454","https://openalex.org/W2099216531","https://openalex.org/W2117366235","https://openalex.org/W2123170466","https://openalex.org/W2128130108","https://openalex.org/W2128372630","https://openalex.org/W2137479650","https://openalex.org/W2151580670","https://openalex.org/W2164420168","https://openalex.org/W2397005828","https://openalex.org/W2523579862","https://openalex.org/W2589714335","https://openalex.org/W2890693932","https://openalex.org/W3105571542","https://openalex.org/W3124253902","https://openalex.org/W4285719527","https://openalex.org/W4308326823","https://openalex.org/W6601540176","https://openalex.org/W6604605561","https://openalex.org/W6727355760"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2358294942","https://openalex.org/W3159405288","https://openalex.org/W1544046904","https://openalex.org/W83344948","https://openalex.org/W2350178533","https://openalex.org/W2102585996","https://openalex.org/W2041190900","https://openalex.org/W2001121861","https://openalex.org/W2350230178"],"abstract_inverted_index":{"First":[0],"name":[1,100,180],"to":[2,13,101,115,181,190],"gender":[3,48,102,142,182,200],"mappings":[4,43,52],"have":[5,84],"been":[6],"widely":[7],"recognized":[8],"as":[9],"a":[10,21,62,75,97,125],"critical":[11],"tool":[12],"complete,":[14],"study":[15,80],"and":[16,47,49,56,88,104,111,128,132,154,171],"validate":[17,134,164],"data":[18,192],"records":[19],"in":[20,124],"range":[22],"of":[23,36,113,143,169,173,179,194],"different":[24],"areas.":[25],"In":[26],"this":[27],"study,":[28],"we":[29,59,95],"investigate":[30],"how":[31,50,81,89],"organizations":[32],"with":[33,64,150],"large":[34],"databases":[35],"existing":[37],"entities":[38],"can":[39,53],"create":[40],"their":[41],"own":[42],"between":[44],"first":[45,60,99],"names":[46],"these":[51],"be":[54],"improved":[55],"utilized.":[57],"Therefore,":[58,184],"explore":[61],"dataset":[63],"demographic":[65],"information":[66,168],"on":[67],"more":[68],"than":[69],"6":[70],"million":[71],"people,":[72],"provided":[73],"by":[74,92,108,137,141],"car":[76],"insurance.":[77],"We":[78,120,146,163],"then":[79],"naming":[82],"conventions":[83],"changed":[85],"over":[86],"time":[87],"they":[90],"differ":[91],"nationality.":[93],"Second,":[94],"build":[96],"probabilistic":[98],"mapping":[103,107,123,136,158],"augment":[105],"the":[106,117,144,148,166,176,198],"adding":[109],"nationality":[110,170],"decade":[112],"birth":[114,174],"improve":[116,175,191],"mapping's":[118],"performance.":[119],"test":[121],"our":[122,135,157],"two":[126],"label":[127,130],"three":[129],"setting":[131],"further":[133],"categorizing":[138],"patent":[139],"filings":[140],"inventor.":[145],"compare":[147],"results":[149],"previous":[151],"studies'":[152],"outcomes":[153],"find":[155],"that":[156,165],"produces":[159],"high":[160],"precision":[161],"results.":[162],"additional":[167],"year":[172],"recall":[177],"scores":[178],"mappings.":[183],"it":[185],"constitutes":[186],"an":[187],"efficient":[188],"process":[189],"quality":[193],"organizations'":[195],"records,":[196],"whenever":[197],"attribute":[199],"is":[201],"missing":[202],"or":[203],"unreliable.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}