Sentiment Analysis on TweetEval
Metric: ALL (higher is better)
Metric: ALL (higher is better)
| # | Model↕ | ALL▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | BERTweet | 67.9 | No | BERTweet: A pre-trained language model for Engli... | 2020-05-20 | Code |
| 2 | RoB-RT | 65.2 | No | XLM-T: Multilingual Language Models in Twitter f... | 2021-04-25 | Code |
| 3 | RoBERTa-Base | 61.3 | No | TweetEval: Unified Benchmark and Comparative Eva... | 2020-10-23 | Code |
| 4 | RoBERTa-Twitter | 61 | No | TweetEval: Unified Benchmark and Comparative Eva... | 2020-10-23 | Code |
| 5 | FastText | 58.1 | No | TweetEval: Unified Benchmark and Comparative Eva... | 2020-10-23 | Code |
| 6 | LSTM | 56.5 | No | TweetEval: Unified Benchmark and Comparative Eva... | 2020-10-23 | Code |
| 7 | SVM | 53.5 | No | TweetEval: Unified Benchmark and Comparative Eva... | 2020-10-23 | Code |