Hate Speech Detection towards the Mexican Spanish Speaking LGBT+ Population (HOMO-MEX)¶
The HOMO-MEX task (webpage) presented at IberLEF 2023 focused on detecting LGBTQ+ phobic content in Spanish tweets.
The following code can generate an instance of the system used in the competition.
>>> from EvoMSA.competitions import Comp2023
>>> D = # Training set
>>> tailored = 'IberLEF2023_HOMO-MEX'
>>> comp2023 = Comp2023(lang='es', tailored=tailored)
>>> ins = comp2023.stack_3_bow_tailored_all_keywords(D)
Configuration |
Performance |
p-value |
---|---|---|
|
0.7914 |
1.0000 |
|
0.7912 |
0.4460 |
|
0.7908 |
0.3420 |
|
0.7904 |
0.2980 |
|
0.7903 |
0.2700 |
|
0.7901 |
0.0740 |
|
0.7885 |
0.1300 |
|
0.7880 |
0.1460 |
|
0.7871 |
0.0660 |
|
0.7861 |
0.0160 |
|
0.7689 |
0.0000 |
|
0.7669 |
0.0000 |
|
0.7553 |
0.0000 |