HUHU - Degree of prejudice prediction

The task offers a frame to study how humour is used to discriminate minorities and to analyse their interplay with the degree of prejudice expressed against specific groups. Given tweets that express prejudices, the task consists on predicting on a continuous scale from 1 to 5 to evaluate how prejudicial the messages are on average. .The tweets are in Spanish and target the following groups: women and feminists, the LGBTI+ community, immigrants and racially discriminated people, and over-weighted people. 

Roberto Labadie Tamayo, Berta Chulvi, Paolo Rosso (2023) Everybody Hurts, Sometimes Overview of HUrtful HUmour at IberLEF 2023: Detection of Humour Spreading Prejudice in Twitter. Procesamiento del Lenguaje Natural, Revista nº 71, septiembre de 2023, pp. 383-395.

Task results

System RMSE
cocalao-1 0.8900
mesichiquito-1 0.8910
M&C-1 0.8550
MJR-1 0.8930
Huhuligans-1 0.8740
MJR-2 0.8930
MosquitosBiased-1 0.8810
Zeroimagination-1 0.8810
CIC-NLP-1 0.8810
ByteMeIfYouCan-1 0.8870

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