EXIST-2025: Sexism categorization in tweets (hard-hard)

Many aspects of a woman’s life can be the target of sexist attitudes, such as domestic and parental roles, professional opportunities, sexual image, and life expectations, among others. Automatically detecting which of these facets are most frequently targeted on social media will facilitate the development of policies to combat sexism. In this task, each sexist tweet must be classified into one or more of the following categories: IDEOLOGICAL AND INEQUALITY, STEREOTYPING AND DOMINANCE, OBJECTIFICATION, SEXUAL VIOLENCE, MISOGYNY AND NON-SEXUAL VIOLENCE. A hard-hard evaluation is considered, where system-predicted labels are compared with the gold standard labels.

Publication
Plaza, L. et al. (2025). Overview of EXIST 2025: Learning with Disagreement for Sexism Identification and Characterization in Tweets, Memes, and TikTok Videos. In: Carrillo-de-Albornoz, J., et al. Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2025. Lecture Notes in Computer Science, vol 16089. Springer, Cham.
Language
Spanish
English
NLP topic
Dataset
Year
2025
Ranking metric
ICM

Task results

System ICM Sort ascending
Mario_1 0.6519
CIMAT-GTO_2 0.5413
CIMAT-GTO_3 0.5211
NLPDame_3 0.4842
NLPDame_1 0.4814

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.