White supremacist language classification on Twitter dataset (test)
0.74AUC (ROC)Alatawi et al. (2021)
Evaluation Results
| Method | Links | |
|---|---|---|
| Alatawi et al. (2021)Model type=BERT2023.06 | 0.74 | |
| WeakTraining source=Weakly annotated data2023.06 | 0.716 | |
| Weak + AnnTraining source=Weakly + Manually annotated data2023.06 | 0.709 | |
| AnnotatedTraining source=Manually annotated data2023.06 | 0.653 | |
| Siegel et al. (2021)Method description=Dictionary match + Naive Bayes classifier2023.06 | 0.603 |