The main purpose of MeOffendEs is to promote research on the detection of offensive language in Spanish variants. This task consists in classifying tweets as offensive or non-offensive in the Offend-MEX corpus, this is, a binary text classification problem. A text is considered as offensive when language is used to commit an explicit or implicitly directed offense that may include insults, threats, profanity or swearing.
Publication
Flor Miriam Plaza-del-Arco, Marco Casavantes, Hugo Jair Escalante, M. Teresa Martín-Valdivia, Arturo Montejo-Ráez, Manuel Montes-y-Gómez, Horacio Jarquín-Vásquez, Luis Villaseñor-Pineda (2021) Overview of MeOffendEs at IberLEF 2021: Offensive Language Detection in Spanish Variants.Procesamiento del Lenguaje Natural, Revista nº 67, septiembre de 2021, pp. 183-194.
Competition
NLP topic
Abstract task
Dataset
Year
2021
Publication link
Task results
System | Precision | Recall | F1 Sort ascending |
---|---|---|---|
CIMAT-MTY-GTO | 0.7600 | 0.6533 | 0.7026 |
NLP-CIC | 0.7550 | 0.6407 | 0.6932 |
DCCD-INFOTEC | 0.6733 | 0.6966 | 0.6847 |
CIMAT-GTO | 0.6633 | 0.6958 | 0.6792 |
UMUTeam | 0.6650 | 0.6763 | 0.6706 |