{"url":"/dataset/dynasent","name":"DynaSent","full_name":null,"description_markdown":"DynaSent is an English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source Dynabench Platform, which facilities human-and-model-in-the-loop dataset creation. DynaSent has a total of 121,634 sentences, each validated by five crowdworkers.\r\n\r\nSource: [DynaSent: A Dynamic Benchmark for Sentiment Analysis](/paper/dynasent-a-dynamic-benchmark-for-sentiment)","description_withheld":null,"homepage":"https://github.com/cgpotts/dynasent","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/dynasent-a-dynamic-benchmark-for-sentiment","title":"DynaSent: A Dynamic Benchmark for Sentiment Analysis","first_author":"Christopher Potts","url":null},"license":null,"modalities":[],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"}],"languages":[],"variants":["DynaSent"],"data_loaders":[{"repo":"https://github.com/cgpotts/dynasent","url":"https://github.com/cgpotts/dynasent","frameworks":["pytorch"]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-dynasent","task":"Sentiment Analysis","dataset_variant":"DynaSent","rows":12,"metrics":["Macro F1","10 fold Cross validation"],"first_row_in_archive_order":{"model":"GPT-4o Fine-Tuned (Minimal)","paper":"/paper/electra-and-gpt-4o-cost-effective-partners","metrics":{"Macro F1":"89"},"code_links":[{"title":"jbeno/sentiment","url":"https://github.com/jbeno/sentiment"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/electra-and-gpt-4o-cost-effective-partners","title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","date":"2024-12-29","rows_on_this_dataset":11,"code_links":1,"syntology":null},{"paper":"/paper/arabic-multi-dialect-segmentation-bi-lstm-crf","title":"Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM","date":"2017-08-19","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"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."}