Explainable Detection of Online Sexism (EDOS)¶
The EDOS task presented at SemEval 2023 aims at the detection of sexism.
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_2_bow_keywords(D)
Configuration |
Performance |
p-value |
---|---|---|
|
0.7622 |
1.0000 |
|
0.7580 |
0.2220 |
|
0.7567 |
0.0960 |
|
0.7532 |
0.1100 |
|
0.7517 |
0.0720 |
|
0.7503 |
0.0600 |
|
0.7502 |
0.0280 |
|
0.7487 |
0.0300 |
|
0.7486 |
0.0540 |
|
0.7478 |
0.0100 |
|
0.7398 |
0.0060 |
|
0.7354 |
0.0020 |
|
0.7350 |
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 |
---|---|---|
|
0.5247 |
1.0000 |
|
0.5123 |
0.1580 |
|
0.5088 |
0.1540 |
|
0.5064 |
0.1040 |
|
0.5002 |
0.1440 |
|
0.4969 |
0.1000 |
|
0.4950 |
0.0960 |
|
0.4929 |
0.0760 |
|
0.4924 |
0.0080 |
|
0.4909 |
0.1000 |
|
0.4597 |
0.0340 |
|
0.4450 |
0.0140 |
|
0.4427 |
0.0140 |
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_2_bow_all_keywords(D)
Configuration |
Performance |
p-value |
---|---|---|
|
0.3236 |
1.0000 |
|
0.3145 |
0.0980 |
|
0.3123 |
0.2760 |
|
0.3069 |
0.1460 |
|
0.3035 |
0.0020 |
|
0.2943 |
0.0580 |
|
0.2924 |
0.0240 |
|
0.2870 |
0.0120 |
|
0.2700 |
0.0140 |
|
0.2685 |
0.0140 |
|
0.2556 |
0.0000 |
|
0.2530 |
0.0080 |
|
0.2486 |
0.0000 |