Abuse Detection on Hate Dataset
92AUCDL-Text & Metadata (Interleaved)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DL-Text & Metadata (Interleaved)Features=Text & Metadata, Training Strategy=Interleaved Training2018.02 | 92 | 90 | 89 | 89 | 89 | |
| DL-Text onlyFeatures=Text only2018.02 | 91 | 87 | 89 | 87 | 88 | |
| DL-Text & Metadata (Tran. Lear.)Features=Text & Metadata, Training Strategy=Transfer Learning2018.02 | 91 | 87 | 89 | 87 | 88 | |
| DL-Text & Metadata (Naive Train.)Features=Text & Metadata, Training Strategy=Naive Training2018.02 | 90 | 87 | 89 | 87 | 88 | |
| DL-Text & Metadata (Tran. Lear. FT)Features=Text & Metadata, Training Strategy=Transfer Learning with Fine-Tuning2018.02 | 90 | 87 | 89 | 87 | 88 | |
| Davidson et al. 20172018.02 | 87 | 89 | 91 | 90 | 90 | |
| DL-Metadata onlyFeatures=Metadata only2018.02 | 75 | 61 | 80 | 61 | 66 | |
| Baseline Naive Bayes2018.02 | 71 | 87 | 84 | 87 | 85 |