It is a multi-class classification task that aims to assign a degree of toxicity to a text (0=not toxic; 1=mildly toxic; 2=toxic and 3=very toxic). The texts considered are comments posted in response to different online news articles related to immigration.
Publication
Mariona Taulé, Alejandro Ariza, Montserrat Nofre, Enrique Amigó, Paolo Rosso (2021) Overview of DETOXIS at IberLEF 2021: DEtection of TOXicity in comments In Spanish. Procesamiento del Lenguaje Natural, Revista nº 67, septiembre de 2021, pp. 209-221.
Competition
NLP topic
Abstract task
Dataset
Year
2021
Publication link
Ranking metric
CEM
Task results
| System | CEM Sort ascending |
|---|---|
| GTH-UPM | 0.7526 |
| SINAI | 0.7495 |
| Team Sabari | 0.7428 |
| DCG | 0.7300 |
| GuillemGSubies | 0.7189 |
