{"url":"/dataset/tweeteval","name":"TweetEval","full_name":null,"description_markdown":"TweetEval introduces an evaluation framework consisting of seven heterogeneous Twitter-specific classification tasks.\r\n\r\nSource: [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](/paper/tweeteval-unified-benchmark-and-comparative)\r\nImage Source: [https://arxiv.org/pdf/2010.12421v2.pdf](https://arxiv.org/pdf/2010.12421v2.pdf)","description_withheld":null,"homepage":"https://github.com/cardiffnlp/tweeteval","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/tweeteval-unified-benchmark-and-comparative","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","first_author":"Francesco Barbieri","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TweetEval","tweet_eval","irony"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cardiffnlp/tweet_eval","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tweet_eval","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/cardiffnlp/tweeteval","url":"https://github.com/cardiffnlp/tweeteval","frameworks":[]}],"num_papers_in_archive":84,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-tweeteval","task":"Sentiment Analysis","dataset_variant":"TweetEval","rows":7,"metrics":["Emoji","Emotion","Hate","Irony","Offensive","Sentiment","Stance","ALL"],"first_row_in_archive_order":{"model":"BERTweet","paper":"/paper/bertweet-a-pre-trained-language-model-for","metrics":{"ALL":"67.9","Emoji":"33.4","Emotion":"79.3","Irony":"82.1","Offensive":"79.5","Sentiment":"73.4","Stance":"71.2"},"code_links":[{"title":"VinAIResearch/BERTweet","url":"https://github.com/VinAIResearch/BERTweet"},{"title":"cardiffnlp/tweeteval","url":"https://github.com/cardiffnlp/tweeteval"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bertweet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/xlm-t-a-multilingual-language-model-toolkit","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","date":"2021-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tweeteval-unified-benchmark-and-comparative","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","date":"2020-10-23","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","date":"2020-05-20","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}