Jekyll institute or Mrs Hyde? gender identification with machine learning

Social media platforms offer an invaluable wealth of data to understand what is taking place in our society. However, social media data hides demographic biases related to characteristics such as gender or age. Therefore, considering social media data as representative of the population can lead to...

ver descrição completa

Detalhes bibliográficos
Autores: Gombert, Arnault, Sánchez-López, Borja, Cerquides, Jesús
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/380399
Acesso em linha:http://hdl.handle.net/10261/380399
https://api.elsevier.com/content/abstract/scopus_id/85215615826
Access Level:acceso abierto
Palavra-chave:Active learning
Bias
Deep learning
Gender
Machine learning
Natural language processing
Twitter
id ES_e7a64751d656a2522cfa4ac4bcf7509f
oai_identifier_str oai:digital.csic.es:10261/380399
network_acronym_str ES
network_name_str España
repository_id_str
spelling Jekyll institute or Mrs Hyde? gender identification with machine learningGombert, ArnaultSánchez-López, BorjaCerquides, JesúsActive learningBiasDeep learningGenderMachine learningNatural language processingTwitterSocial media platforms offer an invaluable wealth of data to understand what is taking place in our society. However, social media data hides demographic biases related to characteristics such as gender or age. Therefore, considering social media data as representative of the population can lead to fallacious interpretations. For instance, in France in 2021, women represent 51.6% of the population1, whereas on Twitter they represent only 33.5% of French users 2. With such a significant difference between social network user demographics and the actual population, detecting the gender or age before delving into a deeper analysis of social phenomena becomes a priority. In this paper, we tackle the gender detection problem on Twitter. We introduce miniAM2, which is an assemblage model of an enriched distillation with weak-supervised learning. Our contributions are threefold: (i) a novel multilingual model that outperforms existing models in both accuracy and speed, allowing for real-time gender detection and organization status on Twitter based on their name, screen_name, and description, making it lighter and faster than state-of-the-art; (ii) an innovative assemblage multi-language strategy that enriches a distillation process with weak-supervised learning using minimal annotated data, and (iii) a unique method to adapt the model to similar languages without requiring annotated data in the target language, which provides significant advancements in handling resource-poor languages in gender detection tasks. We provide our model on demand so social scientists can use it for their analysis.This work is partially supported by the projects Crowd4SDG, GUARDEN, and Humane-AI-net, which have received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements No. 872944, No. 101060693 and No. 952026, respectively.Peer reviewedElsevierEuropean CommissionSánchez-López, Borja [0000-0002-8768-5422]Cerquides, Jesús [0000-0002-3752-644X]Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202520252025info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10261/380399https://api.elsevier.com/content/abstract/scopus_id/85215615826reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/EC/H2020/872944info:eu-repo/grantAgreement/EC/H2020/101060693info:eu-repo/grantAgreement/EC/H2020/952026https://doi.org/10.1016/j.engappai.2025.110087Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/3803992026-05-22T06:33:51Z
dc.title.none.fl_str_mv Jekyll institute or Mrs Hyde? gender identification with machine learning
title Jekyll institute or Mrs Hyde? gender identification with machine learning
spellingShingle Jekyll institute or Mrs Hyde? gender identification with machine learning
Gombert, Arnault
Active learning
Bias
Deep learning
Gender
Machine learning
Natural language processing
Twitter
title_short Jekyll institute or Mrs Hyde? gender identification with machine learning
title_full Jekyll institute or Mrs Hyde? gender identification with machine learning
title_fullStr Jekyll institute or Mrs Hyde? gender identification with machine learning
title_full_unstemmed Jekyll institute or Mrs Hyde? gender identification with machine learning
title_sort Jekyll institute or Mrs Hyde? gender identification with machine learning
dc.creator.none.fl_str_mv Gombert, Arnault
Sánchez-López, Borja
Cerquides, Jesús
author Gombert, Arnault
author_facet Gombert, Arnault
Sánchez-López, Borja
Cerquides, Jesús
author_role author
author2 Sánchez-López, Borja
Cerquides, Jesús
author2_role author
author
dc.contributor.none.fl_str_mv European Commission
Sánchez-López, Borja [0000-0002-8768-5422]
Cerquides, Jesús [0000-0002-3752-644X]
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Active learning
Bias
Deep learning
Gender
Machine learning
Natural language processing
Twitter
topic Active learning
Bias
Deep learning
Gender
Machine learning
Natural language processing
Twitter
description Social media platforms offer an invaluable wealth of data to understand what is taking place in our society. However, social media data hides demographic biases related to characteristics such as gender or age. Therefore, considering social media data as representative of the population can lead to fallacious interpretations. For instance, in France in 2021, women represent 51.6% of the population1, whereas on Twitter they represent only 33.5% of French users 2. With such a significant difference between social network user demographics and the actual population, detecting the gender or age before delving into a deeper analysis of social phenomena becomes a priority. In this paper, we tackle the gender detection problem on Twitter. We introduce miniAM2, which is an assemblage model of an enriched distillation with weak-supervised learning. Our contributions are threefold: (i) a novel multilingual model that outperforms existing models in both accuracy and speed, allowing for real-time gender detection and organization status on Twitter based on their name, screen_name, and description, making it lighter and faster than state-of-the-art; (ii) an innovative assemblage multi-language strategy that enriches a distillation process with weak-supervised learning using minimal annotated data, and (iii) a unique method to adapt the model to similar languages without requiring annotated data in the target language, which provides significant advancements in handling resource-poor languages in gender detection tasks. We provide our model on demand so social scientists can use it for their analysis.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/380399
https://api.elsevier.com/content/abstract/scopus_id/85215615826
url http://hdl.handle.net/10261/380399
https://api.elsevier.com/content/abstract/scopus_id/85215615826
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/EC/H2020/872944
info:eu-repo/grantAgreement/EC/H2020/101060693
info:eu-repo/grantAgreement/EC/H2020/952026
https://doi.org/10.1016/j.engappai.2025.110087
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422873381175296
score 15.812429

Registos relacionados