{"id":"https://openalex.org/W4406709588","doi":"https://doi.org/10.1016/j.engappai.2025.110087","title":"Jekyll institute or Mrs Hyde? gender identification with machine learning","display_name":"Jekyll institute or Mrs Hyde? gender identification with machine learning","publication_year":2025,"publication_date":"2025-01-22","ids":{"openalex":"https://openalex.org/W4406709588","doi":"https://doi.org/10.1016/j.engappai.2025.110087"},"language":"en","primary_location":{"id":"doi:10.1016/j.engappai.2025.110087","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2025.110087","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.engappai.2025.110087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036534955","display_name":"Arnault Gombert","orcid":null},"institutions":[{"id":"https://openalex.org/I42134832","display_name":"Barcelona School of Economics","ror":"https://ror.org/02k09n368","country_code":"ES","type":"education","lineage":["https://openalex.org/I42134832"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Arnault Gombert","raw_affiliation_strings":["Barcelona School of Economics (BSE), Carrer Ramon Trias Fargas, 25-27, Barcelona, 08005, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona School of Economics (BSE), Carrer Ramon Trias Fargas, 25-27, Barcelona, 08005, Spain","institution_ids":["https://openalex.org/I42134832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056416630","display_name":"Borja S\u00e1nchez-L\u00f3pez","orcid":"https://orcid.org/0000-0002-8768-5422"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Borja S\u00e1nchez-L\u00f3pez","raw_affiliation_strings":["Artificial Intelligence Research Institute (IIIA), CSIC, Carrer de Can Planas, Zona 2, Bellaterra, Barcelona, 08193, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8768-5422","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (IIIA), CSIC, Carrer de Can Planas, Zona 2, Bellaterra, Barcelona, 08193, Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014918148","display_name":"Jes\u00fas Cerquides","orcid":"https://orcid.org/0000-0002-3752-644X"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Jesus Cerquides","raw_affiliation_strings":["Artificial Intelligence Research Institute (IIIA), CSIC, Carrer de Can Planas, Zona 2, Bellaterra, Barcelona, 08193, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3752-644X","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (IIIA), CSIC, Carrer de Can Planas, Zona 2, Bellaterra, Barcelona, 08193, Spain","institution_ids":["https://openalex.org/I4210131846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014918148"],"corresponding_institution_ids":["https://openalex.org/I4210131846"],"apc_list":{"value":3170,"currency":"USD","value_usd":3170},"apc_paid":{"value":3170,"currency":"USD","value_usd":3170},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01585206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"144","issue":null,"first_page":"110087","last_page":"110087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9645000100135803,"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":0.9645000100135803,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8775706887245178},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5232119560241699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46743646264076233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44041967391967773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8775706887245178},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5232119560241699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46743646264076233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44041967391967773},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.engappai.2025.110087","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2025.110087","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:digital.csic.es:10261/380399","is_oa":true,"landing_page_url":"https://api.elsevier.com/content/abstract/scopus_id/85215615826","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1016/j.engappai.2025.110087","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2025.110087","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1102291409","display_name":null,"funder_award_id":"101060693","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5464936042","display_name":null,"funder_award_id":"872944","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5542951831","display_name":null,"funder_award_id":"952026","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W122513158","https://openalex.org/W618024573","https://openalex.org/W1821462560","https://openalex.org/W1904365287","https://openalex.org/W1978710835","https://openalex.org/W1984926150","https://openalex.org/W2022783018","https://openalex.org/W2255201980","https://openalex.org/W2498119267","https://openalex.org/W2555691318","https://openalex.org/W2599674900","https://openalex.org/W2769041395","https://openalex.org/W2782446662","https://openalex.org/W2886358838","https://openalex.org/W2951630634","https://openalex.org/W2959716049","https://openalex.org/W2962843773","https://openalex.org/W2978017171","https://openalex.org/W3011414569","https://openalex.org/W3040618662","https://openalex.org/W3101118213","https://openalex.org/W3172009779","https://openalex.org/W3173738993","https://openalex.org/W3183212227","https://openalex.org/W3183859557","https://openalex.org/W3187774863","https://openalex.org/W3197822594","https://openalex.org/W3199635878","https://openalex.org/W3216873837","https://openalex.org/W4233907442","https://openalex.org/W4240035135","https://openalex.org/W4240861383","https://openalex.org/W4253763531","https://openalex.org/W4286447321","https://openalex.org/W4288090629","https://openalex.org/W4308245305","https://openalex.org/W4315630900","https://openalex.org/W4382045926","https://openalex.org/W6632963050","https://openalex.org/W6646509139","https://openalex.org/W6731280071","https://openalex.org/W6751926119","https://openalex.org/W6755207826","https://openalex.org/W6763138596","https://openalex.org/W6764437317","https://openalex.org/W6764526590","https://openalex.org/W6768086466","https://openalex.org/W6768807518","https://openalex.org/W6773357711","https://openalex.org/W6775376942","https://openalex.org/W6784967019","https://openalex.org/W6787673520","https://openalex.org/W6799494012","https://openalex.org/W6801961416"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Social":[0],"media":[1,20,36],"platforms":[2],"offer":[3],"an":[4,127,131,183],"invaluable":[5],"wealth":[6],"of":[7,40,57,72,105,130],"data":[8,21,37,215,269],"to":[9,26,45,205,209,274],"understand":[10],"what":[11],"is":[12,126],"taking":[13],"place":[14],"in":[15,50,52,150,216,224,228],"our":[16,234],"society.":[17],"However,":[18],"social":[19,35,86,106,239],"hides":[22],"demographic":[23],"biases":[24],"related":[25],"characteristics":[27],"such":[28,81],"as":[29,38],"gender":[30,96,117,158,229],"or":[31,97],"age.":[32],"Therefore,":[33],"considering":[34],"representative":[39],"the":[41,58,91,95,116,207,217,249],"population":[42,59],"can":[43,241],"lead":[44],"fallacious":[46],"interpretations.":[47],"For":[48],"instance,":[49],"France":[51],"2021,":[53],"women":[54],"represent":[55,69],"51.6%":[56],"1":[60,61],"https://www.insee.fr/fr/statistiques/6024136":[62],".":[63,78,79],",":[64,169,171,174],"whereas":[65],"on":[66,120,163,166,236],"Twitter":[67,164,256],"they":[68],"only":[70],"33.5%":[71],"French":[73],"users":[74],"2":[75,76],"https://datareportal.com/reports/digital-2021-france":[77],"With":[80],"a":[82,102,109,142,190,202],"significant":[83,222],"difference":[84],"between":[85],"network":[87],"user":[88],"demographics":[89],"and":[90,153,160,172,178,200,258,267],"actual":[92],"population,":[93],"detecting":[94],"age":[98],"before":[99],"delving":[100],"into":[101],"deeper":[103],"analysis":[104],"phenomena":[107],"becomes":[108],"priority.":[110],"In":[111],"this":[112],"paper,":[113],"we":[114],"tackle":[115],"detection":[118,159,230],"problem":[119],"Twitter.":[121],"We":[122,232],"introduce":[123],"miniAM2,":[124],"which":[125,220],"assemblage":[128,185],"model":[129,145,208,235,252,273],"enriched":[132],"distillation":[133,191],"with":[134,193],"weak-supervised":[135,194],"learning.":[136],"Our":[137],"contributions":[138],"are":[139],"threefold:":[140],"(i)":[141],"novel":[143],"multilingual":[144,251],"that":[146,188],"outperforms":[147],"existing":[148],"models":[149],"both":[151],"accuracy":[152],"speed,":[154],"allowing":[155],"for":[156,244],"real-time":[157],"organization":[161],"status":[162],"based":[165],"their":[167,245],"name":[168],"screen_name":[170],"description":[173],"making":[175],"it":[176,243],"lighter":[177],"faster":[179],"than":[180],"state-of-the-art;":[181],"(ii)":[182],"innovative":[184],"multi-language":[186],"strategy":[187],"enriches":[189],"process":[192],"learning":[195],"using":[196],"minimal":[197],"annotated":[198,214,278],"data,":[199],"(iii)":[201],"unique":[203],"method":[204],"adapt":[206],"similar":[210,275],"languages":[211,227,276],"without":[212,277],"requiring":[213],"target":[218,279],"language,":[219],"provides":[221],"advancements":[223],"handling":[225],"resource-poor":[226],"tasks.":[231],"provide":[233],"demand":[237],"so":[238],"scientists":[240],"use":[242],"analysis.":[246],"\u2022":[247,260,271],"Over":[248],"SOTA":[250],"detects":[253],"gender/org.":[254],"from":[255],"names":[257],"descriptions.":[259],"Multi-language":[261],"approach":[262],"enhances":[263],"distillation,":[264],"weak":[265],"supervision,":[266],"low":[268],"use.":[270],"Adapts":[272],"language":[280],"data..":[281]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}