{"id":"https://openalex.org/W2911735741","doi":"https://doi.org/10.1145/3308558.3313684","title":"Demographic Inference and Representative Population Estimates from Multilingual Social Media Data","display_name":"Demographic Inference and Representative Population Estimates from Multilingual Social Media Data","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2911735741","doi":"https://doi.org/10.1145/3308558.3313684","mag":"2911735741"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313684","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313684","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zijian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zijian Wang","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Scott Hale","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Scott Hale","raw_affiliation_strings":["University of Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"David Ifeoluwa Adelani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Ifeoluwa Adelani","raw_affiliation_strings":["Saarland, Germany"],"affiliations":[{"raw_affiliation_string":"Saarland, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Przemyslaw Grabowicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Przemyslaw Grabowicz","raw_affiliation_strings":["Max Planck Institute for Software Systems, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Software Systems, Germany","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Timo Hartman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz-Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Hartman","raw_affiliation_strings":["GESIS, Germany"],"affiliations":[{"raw_affiliation_string":"GESIS, Germany","institution_ids":["https://openalex.org/I4210101898"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fabian Fl\u00f6ck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz-Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Fl\u00f6ck","raw_affiliation_strings":["GESIS, Germany"],"affiliations":[{"raw_affiliation_string":"GESIS, Germany","institution_ids":["https://openalex.org/I4210101898"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Jurgens","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jurgens","raw_affiliation_strings":["University of Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":24.721,"has_fulltext":false,"cited_by_count":175,"citation_normalized_percentile":{"value":0.99623031,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2056","last_page":"2067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10557","display_name":"Social Media and Politics","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/T10557","display_name":"Social Media and Politics","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9883999824523926,"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/T13718","display_name":"Media Influence and Politics","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7723000049591064},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6226999759674072},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5527999997138977},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.42809998989105225},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.39410001039505005},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3765000104904175},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.3312999904155731}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7723000049591064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6877999901771545},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098000168800354},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45890000462532043},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4043999910354614},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.31470000743865967},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C169733012","wikidata":"https://www.wikidata.org/wiki/Q1613416","display_name":"Population size","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C126349790","wikidata":"https://www.wikidata.org/wiki/Q905036","display_name":"Computational sociology","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3308558.3313684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313684","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.05961","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.05961","pdf_url":"https://arxiv.org/pdf/1905.05961","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313684","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W285374334","https://openalex.org/W1541992550","https://openalex.org/W2017729405","https://openalex.org/W2018690609","https://openalex.org/W2031046474","https://openalex.org/W2048679005","https://openalex.org/W2064675550","https://openalex.org/W2068015998","https://openalex.org/W2073443734","https://openalex.org/W2099977142","https://openalex.org/W2105602542","https://openalex.org/W2111666304","https://openalex.org/W2116646433","https://openalex.org/W2117239687","https://openalex.org/W2136645636","https://openalex.org/W2147481677","https://openalex.org/W2152460337","https://openalex.org/W2166730394","https://openalex.org/W2251566237","https://openalex.org/W2251812186","https://openalex.org/W2255201980","https://openalex.org/W2510725918","https://openalex.org/W2547314356","https://openalex.org/W2567013901","https://openalex.org/W2567282614","https://openalex.org/W2610685155","https://openalex.org/W2754977407","https://openalex.org/W2764332164","https://openalex.org/W2807090052","https://openalex.org/W2891161640","https://openalex.org/W2963251942","https://openalex.org/W2963783540","https://openalex.org/W2963965928","https://openalex.org/W4229494989","https://openalex.org/W4234222179","https://openalex.org/W6640598943","https://openalex.org/W6725739302"],"related_works":[],"abstract_inverted_index":{"Social":[0],"media":[1,107],"provide":[2],"access":[3],"to":[4,17,27,49,61,78],"behavioural":[5],"data":[6,16],"at":[7],"an":[8],"unprecedented":[9],"scale":[10],"and":[11,30,40,59,103,149],"granularity.":[12],"However,":[13],"using":[14],"these":[15,69],"understand":[18],"phenomena":[19],"in":[20,63,111],"a":[21,64,80,91],"broader":[22],"population":[23,83,147,151],"is":[24],"difficult":[25],"due":[26],"their":[28],"non-representativeness":[29],"the":[31,121],"bias":[32],"of":[33,100,105,120],"statistical":[34],"inference":[35,45,75],"tools":[36],"towards":[37],"dominant":[38],"languages":[39],"groups.":[41],"While":[42],"demographic":[43,74,87],"attribute":[44],"could":[46],"be":[47],"used":[48],"mitigate":[50],"such":[51],"bias,":[52],"current":[53,118],"techniques":[54],"are":[55],"almost":[56],"entirely":[57],"monolingual":[58],"fail":[60],"work":[62],"global":[65],"environment.":[66],"We":[67],"address":[68],"challenges":[70],"by":[71],"combining":[72],"multilingual":[73],"with":[76],"post-stratification":[77],"create":[79,90],"more":[81],"representative":[82],"sample.":[84],"To":[85,128],"learn":[86],"attributes,":[88],"we":[89,133],"new":[92],"multimodal":[93],"deep":[94],"neural":[95],"architecture":[96],"for":[97,130],"joint":[98,146],"classification":[99],"age,":[101],"gender,":[102],"organization-status":[104],"social":[106],"users":[108],"that":[109,140],"operates":[110],"32":[112],"languages.":[113],"This":[114],"method":[115],"substantially":[116],"outperforms":[117],"state":[119],"art":[122],"while":[123],"also":[124],"reducing":[125],"algorithmic":[126],"bias.":[127],"correct":[129],"sampling":[131],"biases,":[132],"propose":[134],"fully":[135],"interpretable":[136],"multilevel":[137],"regression":[138],"methods":[139],"estimate":[141],"inclusion":[142],"probabilities":[143],"from":[144],"inferred":[145],"counts":[148],"ground-truth":[150],"counts.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-02-21T00:00:00"}