TweetEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text Classification | TweetEval | Accuracy72.69 | 112 | |
| Text Classification | TweetEVAL (test) | Accuracy (A)84.17 | 44 | |
| Detection | TweetEval hate | Macro F167.53 | 21 | |
| Tweet Classification | TweetEval 1.0 (test) | Emoji (M-F1)34.2 | 18 | |
| Emotion Classification | TweetEval Emotion | Macro-F168.74 | 15 | |
| Twitter Text Classification | TweetEval latest (test) | Emoji0.297 | 9 | |
| Sentiment Prediction | TweetEval (IID) | Accuracy53.1 | 8 | |
| Text Classification | TweetEval Offensive (test) | Accuracy69.14 | 8 | |
| Text Classification | TweetEval Hate (test) | Accuracy55.72 | 8 | |
| Pruning | TweetEval T-Sentiment (test) | AU-MSE1.23 | 8 | |
| Pruning | TweetEval T-Hate (test) | AU-MSE4.88 | 8 | |
| Pruning | TweetEval T-Emotions (test) | AU-MSE1.47 | 8 | |
| Irony Detection | TweetEval irony (test) | Accuracy84.18 | 7 | |
| Detection | TweetEval offensive | Macro F168.3 | 6 | |
| Detection | TweetEval irony | Macro F162.7 | 6 | |
| Detection | TweetEval stance-feminist (test) | Macro F141.3 | 6 | |
| Safety Evaluation | TweetEval | F172 | 3 | |
| Detection | TweetEval stance-atheism | Macro F127.4 | 3 | |
| Detection | TweetEval stance-atheism (TW-A) (test) | Macro-F10.285 | 3 | |
| Detection | TweetEval-offensive (Tw-O) (test) | Macro F156.3 | 3 | |
| Detection | TweetEval-hate (Tw-H) (test) | Macro F159 | 3 |
Showing 21 of 21 rows