Tweet Classification on TweetEval 1.0 (test)
34.2Emoji (M-F1)QA-BPE-nlp + BERTweet
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| QA-BPE-nlp + BERTweetBackbone=BERTweet, Tokenizer=QA-BPE-nlp2026.02 | 34.2 | 81.5 | 58.8 | 82.9 | 83 | 75.1 | 73.5 | 70 | — | |
| TimeLMs-20212026.02 | 34 | 80.2 | 55.1 | 64.5 | 82.2 | 73.7 | 72.9 | 66.2 | — | |
| SotAUnderlying Method=BERTweet2021.04 | 33.4 | 79.3 | 56.4 | 82.1 | 79.5 | 73.4 | 71.2 | 67.9 | — | |
| BERTweet2026.02 | 33.4 | 79.3 | 56.4 | 82.1 | 79.5 | 73.4 | 71.2 | 67.9 | — | |
| RoB-RTBackbone=RoBERTa-Retrained2021.04 | 31.4 | 78.5 | 52.3 | 61.7 | 80.5 | 72.6 | 69.3 | 65.2 | — | |
| RoBERTa-RetrainedBackbone=RoBERTa2026.02 | 31.4 | 78.5 | 52.3 | 61.7 | 80.5 | 72.8 | 69.3 | 65.2 | — | |
| RoB-BsBackbone=RoBERTa-Base2021.04 | 30.9 | 76.1 | 46.6 | 59.7 | 79.5 | 71.3 | 68 | 61.3 | — | |
| XLM-TwBackbone=XLM-Twitter2021.04 | 30.9 | 77 | 50.8 | 69.9 | 79.9 | 72.3 | 67.1 | 64.4 | — | |
| RoBERTa-BaseBackbone=RoBERTa2026.02 | 30.9 | 76.1 | 46.6 | 59.7 | 79.5 | 71.3 | 68 | 61.3 | — | |
| SVM2021.04 | 29.3 | 64.7 | 36.7 | 61.7 | 52.3 | 62.9 | 67.3 | 53.5 | — | |
| RoB-TwBackbone=RoBERTa-Twitter2021.04 | 29.3 | 72 | 46.9 | 65.4 | 77.1 | 69.1 | 66.7 | 61 | — | |
| RoBERTa-TwitterBackbone=RoBERTa2026.02 | 29.3 | 72 | 49.9 | 65.4 | 77.1 | 69.1 | 66.7 | 61.4 | — | |
| SVM2026.02 | 29.3 | 64.7 | 36.7 | 61.7 | 52.3 | 62.9 | 67.3 | 53.5 | — | |
| XLM-RBackbone=XLM-RoBERTa2021.04 | 28.6 | 72.3 | 44.4 | 57.4 | 75.7 | 68.6 | 65.4 | 57.6 | — | |
| FastText2021.04 | 25.8 | 65.2 | 50.6 | 63.1 | 73.4 | 62.9 | 65.4 | 58.1 | — | |
| FastText2026.02 | 25.8 | 65.2 | 50.6 | 63.1 | 73.4 | 62.9 | 65.4 | 58.1 | — | |
| BLSTM2021.04 | 24.7 | 66 | 52.6 | 62.8 | 71.7 | 58.3 | 59.4 | 56.5 | — | |
| LSTM2026.02 | 24.7 | 66 | 52.6 | 62.8 | 71.7 | 58.3 | 59.4 | 56.5 | — | |
| RoBERTa-large (Context Calibration)Model=RoBERTa-large, Setting=CC, Evaluation protocol=Zero-shot prompting2023.05 | — | — | — | — | — | — | — | — | 30.8 | |
| RoBERTa-large (Domain-context Calibration)Model=RoBERTa-large, Setting=DC, Evaluation protocol=Zero-shot prompting2023.05 | — | — | — | — | — | — | — | — | 49.7 | |
| RoBERTa-large (Original)Model=RoBERTa-large, Setting=Original, Evaluation protocol=Zero-shot prompting2023.05 | — | — | — | — | — | — | — | — | 30.5 |