{"url":"/dataset/mr","name":"MR","full_name":"MR Movie Reviews","description_markdown":"**MR** Movie Reviews is a dataset for use in sentiment-analysis experiments. Available are collections of movie-review documents labeled with respect to their overall sentiment polarity (positive or negative) or subjective rating (e.g., \"two and a half stars\") and sentences labeled with respect to their subjectivity status (subjective or objective) or polarity.\n\nSource: [http://www.cs.cornell.edu/people/pabo/movie-review-data/](http://www.cs.cornell.edu/people/pabo/movie-review-data/)\nImage Source: [https://storage.googleapis.com/kaggle-competitions/kaggle/3810/media/treebank.png](https://storage.googleapis.com/kaggle-competitions/kaggle/3810/media/treebank.png)","description_withheld":null,"homepage":"http://www.cs.cornell.edu/people/pabo/movie-review-data/","introduced_date":"2004-01-01","introduced_date_note":null,"introduced_by":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":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"}],"languages":[],"variants":["MR","rotten_tomatoes"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cornell-movie-review-data/rotten_tomatoes","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rotten_tomatoes","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-mr","task":"Sentiment Analysis","dataset_variant":"MR","rows":19,"metrics":["Accuracy","Training Time"],"first_row_in_archive_order":{"model":"VLAWE","paper":"/paper/vector-of-locally-aggregated-word-embeddings","metrics":{"Accuracy":"93.3"},"code_links":[{"title":"raduionescu/vlawe-boswe","url":"https://github.com/raduionescu/vlawe-boswe"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-mr","task":"Text Classification","dataset_variant":"MR","rows":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VLAWE","paper":"/paper/vector-of-locally-aggregated-word-embeddings","metrics":{"Accuracy":"93.3"},"code_links":[{"title":"raduionescu/vlawe-boswe","url":"https://github.com/raduionescu/vlawe-boswe"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-learning-on-mr","task":"Few-Shot Learning","dataset_variant":"MR","rows":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"DART","paper":"/paper/differentiable-prompt-makes-pre-trained","metrics":{"Acc":"88.2(1.0)"},"code_links":[{"title":"zjunlp/DART","url":"https://github.com/zjunlp/DART"},{"title":"zhengxiangshi/powerfulpromptft","url":"https://github.com/zhengxiangshi/powerfulpromptft"},{"title":"paperspapers/badprompt","url":"https://github.com/paperspapers/badprompt"},{"title":"zhaohan-xi/plm-prompt-defense","url":"https://github.com/zhaohan-xi/plm-prompt-defense"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":7,"code_links":1,"syntology":null},{"paper":"/paper/differentiable-prompt-makes-pre-trained","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","date":"2021-08-30","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bertgcn-transductive-text-classification-by","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","date":"2021-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distributed-word-representation-in-tsetlin","title":"Enhancing Interpretable Clauses Semantically using Pretrained Word Representation","date":"2021-04-14","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/simple-spectral-graph-convolution","title":"Simple Spectral Graph Convolution","date":"2021-01-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/graph-star-net-for-generalized-multi-task-1","title":"Graph Star Net for Generalized Multi-Task Learning","date":"2019-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190600095","title":"The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning","date":"2019-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vector-of-locally-aggregated-word-embeddings","title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","date":"2019-02-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/simplifying-graph-convolutional-networks","title":"Simplifying Graph Convolutional Networks","date":"2019-02-19","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-convolutional-networks-for-text","title":"Graph Convolutional Networks for Text Classification","date":"2018-09-15","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-multi-sentiment-resource-enhanced-attention","title":"A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification","date":"2018-07-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improved-sentence-modeling-using-suffix","title":"Improved Sentence Modeling using Suffix Bidirectional LSTM","date":"2018-05-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-la-carte-embedding-cheap-but-effective","title":"A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors","date":"2018-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sentence-state-lstm-for-text-representation","title":"Sentence-State LSTM for Text Representation","date":"2018-05-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/universal-sentence-encoder","title":"Universal Sentence Encoder","date":"2018-03-29","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":22,"samples_ran":1,"samples_unverified":21,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/investigating-capsule-networks-with-dynamic","title":"Investigating Capsule Networks with Dynamic Routing for Text Classification","date":"2018-03-29","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/sentiment-analysis-by-capsules","title":"Sentiment Analysis by Capsules","date":"2018-02-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/using-millions-of-emoji-occurrences-to-learn","title":"Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm","date":"2017-08-01","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+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/all-but-the-top-simple-and-effective","title":"All-but-the-Top: Simple and Effective Postprocessing for Word Representations","date":"2017-02-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":26,"samples_ran":2,"samples_unverified":24,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":10,"samples_harvested":90,"samples_ran":22,"samples_unverified":68,"pointer_only_for_licence":8,"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."}