Abuse Detection on Sarcasm Dataset
98AUCDL-Text & Metadata (Interleaved)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DL-Text & Metadata (Interleaved)Features=Text & Metadata, Training Strategy=Interleaved Training2018.02 | 98 | 97 | 96 | 97 | 97 | |
| DL-Text & Metadata (Naive Train.)Features=Text & Metadata, Training Strategy=Naive Training2018.02 | 97 | 96 | 96 | 96 | 96 | |
| DL-Text & Metadata (Tran. Lear.)Features=Text & Metadata, Training Strategy=Transfer Learning2018.02 | 97 | 95 | 95 | 95 | 95 | |
| DL-Text & Metadata (Tran. Lear. FT)Features=Text & Metadata, Training Strategy=Transfer Learning with Fine-Tuning2018.02 | 97 | 95 | 95 | 95 | 95 | |
| DL-Metadata onlyFeatures=Metadata only2018.02 | 96 | 92 | 94 | 92 | 92 | |
| DL-Text onlyFeatures=Text only2018.02 | 81 | 89 | 89 | 89 | 89 | |
| Rajadesingan, Zafarani, and Liu 20152018.02 | 70 | 93 | — | — | — | |
| Baseline Naive Bayes2018.02 | 66 | 90 | 89 | 90 | 89 |