This is a multi-class classification tasks. The systems have to decide whether or not a given tweet contains sexist expressions or behaviours (i.e., it is sexist itself, describes a sexist situation or criticizes a sexist behaviour) and, if so, to categorize the message according to the type of sexism (according to the categorization proposed by experts and that takes into account the different facets of women that are undermined): (i) ideological and inequality, (ii) stereotyping and dominance, (iii) objectification, (iv) sexual violence, and (v) misogyny and non-sexual violence.
Publicación
Francisco Rodríguez-Sánchez, Jorge Carrillo-de-Albornoz, Laura Plaza, Adrián Mendieta-Aragón, Guillermo Marco-Remón, Maryna Makeienko, María Plaza, Julio Gonzalo, Damiano Spina, Paolo Rosso (2022) Overview of EXIST 2022: sEXism Identification in Social neTworks. Procesamiento del Lenguaje Natural, Revista nº 69, septiembre de 2022, pp. 229-240.
Idioma
Inglés
URL Tarea
NLP topic
Tarea abstracta
Dataset
Año
2022
Enlace publicación
Métrica Ranking
Macro F1
Mejores resultados para la tarea
Sistema | F1 Ordenar ascendente | Accuracy | MacroF1 | Pearson correlation | ICM |
---|---|---|---|---|---|
Roberta large | 0.5846 | 0.5846 | 0.5846 | 0.5846 | 0.58 |
Distilbert base uncased | 0.5486 | 0.5486 | 0.5486 | 0.5486 | 0.55 |
Xlm roberta large | 0.5422 | 0.5422 | 0.5422 | 0.5422 | 0.54 |
Xlm roberta base | 0.5345 | 0.5345 | 0.5345 | 0.5345 | 0.53 |
Bert base cased | 0.5344 | 0.5344 | 0.5344 | 0.5344 | 0.53 |
Ixa ehu ixambert base cased | 0.5300 | 0.5300 | 0.5300 | 0.5300 | 0.53 |
Roberta base | 0.5258 | 0.5258 | 0.5258 | 0.5258 | 0.53 |
Bert base multilingual cased | 0.5022 | 0.5022 | 0.5022 | 0.5022 | 0.50 |
Distilbert base multilingual cased | 0.4792 | 0.4792 | 0.4792 | 0.4792 | 0.48 |