PoliticES: Political Ideology Detection in Spanish Texts

The aim of the PoliticES 2023 shared task is to extract two demographic traits (gender and profession) and one psychographic trait (political ideology) from clusters of tweets from users who share these characteristics. Document classification is approached from a binary and multiclass perspective with four different classes (gender, profession, political ideology binary and multi class. Tweets are collected fromTwitter accounts of politicians, political journalists, and celebrities in Spain.

Publication
José Antonio Garcia-Díaz, Salud María Jiménez-Zafra, María-Teresa Martín-Valdivia, Francisco García-Sánchez, Luis Alfonso Ureña-López, Rafael Valencia-García (2023) Overview of PoliticES at IberLEF 2023: Political Ideology Detection in Spanish Texts Procesamiento del Lenguaje Natural, Revista nº 71, septiembre de 2023, pp. 409-416.
Language
Spanish
NLP topic
Abstract task
Dataset
Year
2023
Ranking metric
Macro F1

Task results

System MacroF1
INFOTEC-LaBD 0.7653
UMUTeam 0.6922
NLP_URJC 0.6756
ELiRF-VRAIN 0.8113
Dataverse 0.6666
HiTZ-Ixa 0.7934
UC3M 0.5943
ESCOM-IPN 0.7852
INGEOTEC 0.7775
Jorge-Owl 0.7717

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.