{"url":"/dataset/sst-2","name":"SST-2","full_name":null,"description_markdown":"The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed with the Stanford parser and includes a total of 215,154 unique phrases from those parse trees, each annotated by 3 human judges.\r\n\r\nBinary classification experiments on full sentences (negative or somewhat negative vs somewhat positive or positive with neutral sentences discarded) refer to the dataset as SST-2 or SST binary.","description_withheld":null,"homepage":"https://github.com/YJiangcm/SST-2-sentiment-analysis","introduced_date":"2013-10-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/recursive-deep-models-for-semantic","title":"Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank","first_author":"Richard Socher","url":null},"license":null,"modalities":[],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"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":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Explanation Fidelity Evaluation","url":"/task/explanation-fidelity-evaluation","datasets_with_task":"/datasets/task/explanation-fidelity-evaluation"},{"name":"Chinese Sentiment Analysis","url":"/task/chinese-sentiment-analysis","datasets_with_task":"/datasets/task/chinese-sentiment-analysis"}],"languages":[],"variants":["SST-2 Binary classification","SST-2 Binary classification Dev","SST2","sst2-es-mt"],"data_loaders":[{"repo":"https://github.com/p-lambda/dsir","url":"https://github.com/p-lambda/dsir","frameworks":["pytorch"]}],"num_papers_in_archive":1808,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/classification-on-sst-2","task":"Classification","dataset_variant":"SST-2","rows":2,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"OPT-1.3B","paper":"/paper/achieving-dimension-free-communication-in","metrics":{"Test Accuracy":"90.78%"},"code_links":[{"title":"ZidongLiu/DeComFL","url":"https://github.com/ZidongLiu/DeComFL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-sst-2","task":"Text Classification","dataset_variant":"SST-2","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DeBERTa","paper":"/paper/transformers-are-short-text-classifiers-a","metrics":{"Accuracy":"94.78"},"code_links":[{"title":"FKarl/short-text-classification","url":"https://github.com/FKarl/short-text-classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/achieving-dimension-free-communication-in","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","date":"2024-05-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transformers-are-short-text-classifiers-a","title":"Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets","date":"2022-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"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."}