The objective of this task is to predict the label of a tweet based on its content. A tweet can be LGBT+phobic (P) if it contains hate speech against people whose sexual orientation or gender identity differs from cisheterosexuality; Non-LGBT+phobic (NP) if it mentions the LGBT+ community without including hate speech; or Unrelated to LGBT+ (NR) if it has no relation to this community.
Publication
Gómez-Adorno et al. (2024). Overview of HOMO-MEX at IberLEF 2024: Hate Speech Detection Towards the Mexican Spanish speaking LGBT+ Population. Procesamiento del Lenguaje Natural, Revista, 73: 393-405.
Language
Spanish (Mexico)
NLP topic
Dataset
Year
2024
Publication link
Task results
| System | MacroF1 Sort ascending |
|---|---|
| VerbaNexAI | 0.9143 |
| CANTeam | 0.8775 |
| I2C-UHU | 0.8765 |
| DSVS | 0.8713 |
| LabTL-INAOE | 0.8563 |
