{"id":"https://openalex.org/W2167479345","doi":"https://doi.org/10.1145/1557019.1557032","title":"Name-ethnicity classification from open sources","display_name":"Name-ethnicity classification from open sources","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2167479345","doi":"https://doi.org/10.1145/1557019.1557032","mag":"2167479345"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083138031","display_name":"Anurag Anil Ambekar","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Ambekar","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005917791","display_name":"Charles B. Ward","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Ward","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104019360","display_name":"Jahangir Mohammed","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jahangir Mohammed","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018801948","display_name":"Swapna Male","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swapna Male","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060741187","display_name":"Steven Skiena","orcid":"https://orcid.org/0000-0003-0397-7514"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Skiena","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":240,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12970","display_name":"Names, Identity, and Discrimination Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12970","display_name":"Names, Identity, and Discrimination Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12749","display_name":"Race, Genetics, and Society","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12728","display_name":"Demographic Trends and Gender Preferences","score":0.9409999847412109,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ethnic-group","display_name":"Ethnic group","score":0.7516593933105469},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7494286894798279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6071398854255676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5714845061302185},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5628596544265747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5030190348625183},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4375946521759033},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.41337287425994873},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37024277448654175},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33582693338394165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3283292055130005},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.20250049233436584},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12897267937660217}],"concepts":[{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.7516593933105469},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7494286894798279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6071398854255676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5714845061302185},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5628596544265747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5030190348625183},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4375946521759033},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.41337287425994873},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37024277448654175},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33582693338394165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3283292055130005},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.20250049233436584},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12897267937660217},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1557019.1557032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.563.9048","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.563.9048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sunysb.edu/~skiena/lydia/names.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W3665932","https://openalex.org/W137202426","https://openalex.org/W198736415","https://openalex.org/W1559247356","https://openalex.org/W1578007978","https://openalex.org/W1970436288","https://openalex.org/W2019968362","https://openalex.org/W2030657688","https://openalex.org/W2054004588","https://openalex.org/W2124692188","https://openalex.org/W2133952599","https://openalex.org/W2134685109","https://openalex.org/W2146610267","https://openalex.org/W2148005820","https://openalex.org/W2155129033","https://openalex.org/W2155313075","https://openalex.org/W2159819284","https://openalex.org/W2167458573","https://openalex.org/W2182050623","https://openalex.org/W2472798435","https://openalex.org/W2640059720","https://openalex.org/W6680105712"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W2381483116","https://openalex.org/W3145575561","https://openalex.org/W4382934300","https://openalex.org/W2121061354","https://openalex.org/W4285388059"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,10,26,97],"ethnicity":[3,28],"identification":[4],"from":[5,36,83],"names":[6,56,82],"has":[7],"a":[8,84],"variety":[9],"important":[11],"applications,":[12],"including":[13],"biomedical":[14],"research,":[15],"demographic":[16],"studies,":[17],"and":[18,51,91],"marketing.":[19],"Here":[20],"we":[21],"report":[22],"on":[23,94],"the":[24,95],"development":[25],"an":[27],"classifier":[29,45,77],"where":[30],"all":[31],"training":[32],"data":[33],"is":[34],"extracted":[35],"public,":[37],"non-confidential":[38],"(and":[39],"hence":[40],"somewhat":[41],"unreliable)":[42],"sources.":[43],"Our":[44],"uses":[46],"hidden":[47],"Markov":[48],"models":[49],"(HMMs)":[50],"decision":[52],"trees":[53],"to":[54,67,78],"classify":[55],"into":[57],"13":[58],"cultural/ethnic":[59,99],"groups":[60],"with":[61],"individual":[62],"group":[63],"accuracy":[64,66],"comparable":[65],"earlier":[68],"binary":[69],"(e.g.,":[70],"Spanish/non-Spanish)":[71],"classifiers.":[72],"We":[73],"have":[74],"applied":[75],"this":[76],"over":[79],"20":[80],"million":[81],"large-scale":[85],"news":[86],"corpus,":[87],"identifying":[88],"interesting":[89],"temporal":[90],"spatial":[92],"trends":[93],"representation":[96],"particular":[98],"groups.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
