{"id":"https://openalex.org/W4320024031","doi":"https://doi.org/10.1109/bigdata55660.2022.10020166","title":"Debiased Learning of Self-Labeled Twitter Data for User Demographic Prediction","display_name":"Debiased Learning of Self-Labeled Twitter Data for User Demographic Prediction","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024031","doi":"https://doi.org/10.1109/bigdata55660.2022.10020166"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020166","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5100422381","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8637-8375"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China","Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032101363","display_name":"Madison Cooley","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madison Cooley","raw_affiliation_strings":["University of Utah,School of Computing,Salt Lake City,USA","School of Computing, University of Utah, Salt Lake City, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah,School of Computing,Salt Lake City,USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"School of Computing, University of Utah, Salt Lake City, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354569","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6777-3487"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China","Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023655697","display_name":"Chao Lan","orcid":"https://orcid.org/0000-0003-2526-7206"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Lan","raw_affiliation_strings":["University of Oklahoma,School of Computer Science,Norman,USA","School of Computer Science, University of Oklahoma, Norman, USA"],"affiliations":[{"raw_affiliation_string":"University of Oklahoma,School of Computer Science,Norman,USA","institution_ids":["https://openalex.org/I8692664"]},{"raw_affiliation_string":"School of Computer Science, University of Oklahoma, Norman, USA","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329259","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-1244-2880"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["University of Southern Queensland,School of Mathematics, Physics and Computing,Toowoomba,Australia","School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"affiliations":[{"raw_affiliation_string":"University of Southern Queensland,School of Mathematics, Physics and Computing,Toowoomba,Australia","institution_ids":["https://openalex.org/I185523456"]},{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100422381"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20555915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6827","last_page":"6829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9897000193595886,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9897000193595886,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.7164912223815918},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6679777503013611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6244964003562927},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6144694089889526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5194875001907349},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5123113393783569},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4849417507648468},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4244399666786194},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19656264781951904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14686319231987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7164912223815918},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6679777503013611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244964003562927},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6144694089889526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5194875001907349},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5123113393783569},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4849417507648468},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4244399666786194},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19656264781951904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14686319231987},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020166","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W123476658","https://openalex.org/W2112483442","https://openalex.org/W2345019564","https://openalex.org/W2758820997","https://openalex.org/W2799159261","https://openalex.org/W2963626623"],"related_works":["https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3171520305","https://openalex.org/W1924178503","https://openalex.org/W3162204513","https://openalex.org/W4308716060","https://openalex.org/W4280648719","https://openalex.org/W3135126032","https://openalex.org/W4386937079"],"abstract_inverted_index":{"Labeling":[0],"sufficient":[1],"data":[2,23,56,81,101,127,134],"for":[3],"supervised":[4],"learning":[5,131],"remains":[6],"an":[7,69,123],"open":[8],"challenge":[9],"in":[10,135],"social":[11,136],"network":[12,137],"analysis.":[13,138],"An":[14],"alternative":[15],"is":[16],"to":[17,99],"collect":[18],"self-labeled":[19,42,55,80,133],"data,":[20,43],"i.e.":[21],"the":[22,45,62,73,104,126],"labeled":[24],"by":[25],"their":[26],"owners.":[27],"Emmery":[28],"et":[29],"al":[30],"show":[31,72,112],"that":[32,97],"standard":[33],"models":[34],"can":[35],"be":[36,59],"trained":[37,78],"and":[38],"perform":[39],"well":[40,85],"on":[41,79,86],"suggesting":[44],"effectiveness":[46],"of":[47,61,125],"this":[48,51],"approach.":[49],"In":[50,109],"paper,":[52],"we":[53,71,111],"argue":[54],"may":[57],"not":[58,83],"representative":[60],"population.":[63],"Taking":[64],"Twitter":[65],"demographic":[66],"prediction":[67],"as":[68],"example,":[70],"popular":[74],"FastText":[75],"model":[76],"standardly":[77],"does":[82],"generalize":[84],"random":[87],"testing":[88],"samples.":[89],"We":[90],"then":[91],"present":[92],"a":[93],"new":[94],"learner":[95],"DeFastText":[96],"aims":[98],"correct":[100],"bias":[102,128],"using":[103],"kernel":[105],"means":[106],"matching":[107],"technique.":[108],"experiment,":[110],"it":[113],"achieves":[114],"lower":[115],"generalization":[116],"errors":[117],"than":[118],"FastText.":[119],"This":[120],"research":[121],"raises":[122],"attention":[124],"problem":[129],"when":[130],"from":[132]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}