Multilingual Hope Speech Detection (HOPE)¶
The HOPE task (webpage) presented at IberLEF 2023 focused on the identification of positive speech in Spanish and English.
The following code can generate an instance of the system used in the competition.
>>> from EvoMSA.competitions import Comp2023
>>> D = # Training set
>>> comp2023 = Comp2023(lang='es')
>>> ins = comp2023.stack_bow_keywords_emojis_voc_selection(D)
Configuration |
Performance |
p-value |
---|---|---|
|
0.8224 |
1.0000 |
|
0.8217 |
0.3580 |
|
0.8192 |
0.3680 |
|
0.8192 |
0.3040 |
|
0.8192 |
0.3680 |
|
0.8159 |
0.1740 |
|
0.8152 |
0.1500 |
|
0.8119 |
0.1020 |
|
0.7998 |
0.0460 |
|
0.7966 |
0.0260 |
|
0.7966 |
0.0260 |
|
0.7902 |
0.0040 |
|
0.7807 |
0.0000 |
The following code can generate an instance of the system used in the competition.
>>> from EvoMSA.competitions import Comp2023
>>> D = # Training set
>>> comp2023 = Comp2023(lang='en')
>>> ins = comp2023.stack_bow_keywords_emojis(D)
Configuration |
Performance |
p-value |
---|---|---|
|
0.7807 |
1.0000 |
|
0.7801 |
0.4600 |
|
0.7753 |
0.2860 |
|
0.7691 |
0.0300 |
|
0.7690 |
0.0260 |
|
0.7680 |
0.0220 |
|
0.7662 |
0.0120 |
|
0.7661 |
0.0200 |
|
0.7640 |
0.0120 |
|
0.7575 |
0.0020 |
|
0.7379 |
0.0020 |
|
0.7300 |
0.0000 |
|
0.7221 |
0.0000 |