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
Publication link
Ranking metric
Macro F1
Task results
System | MacroF1 Sort ascending |
---|---|
ELiRF-VRAIN | 0.8113 |
HiTZ-Ixa | 0.7934 |
ESCOM-IPN | 0.7852 |
INGEOTEC | 0.7775 |
Jorge-Owl | 0.7717 |
INFOTEC-LaBD | 0.7653 |
UMUTeam | 0.6922 |
NLP_URJC | 0.6756 |
Dataverse | 0.6666 |
UC3M | 0.5943 |