{"url":"/dataset/subj","name":"SUBJ","full_name":"Subjectivity dataset","description_markdown":"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.\r\n\r\nSource: [SUBJ](http://www.cs.cornell.edu/people/pabo/movie-review-data/)","description_withheld":null,"homepage":"http://www.cs.cornell.edu/people/pabo/movie-review-data/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Subjectivity Analysis","url":"/task/subjectivity-analysis","datasets_with_task":"/datasets/task/subjectivity-analysis"}],"languages":[],"variants":["SUBJ"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/subjectivity-analysis-on-subj","task":"Subjectivity Analysis","dataset_variant":"SUBJ","rows":19,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RoBERTa+DualCL","paper":"/paper/dual-contrastive-learning-text-classification","metrics":{"Accuracy":"97.34"},"code_links":[{"title":"hiyouga/dual-contrastive-learning","url":"https://github.com/hiyouga/dual-contrastive-learning"},{"title":"hiyouga/hiyouga","url":"https://github.com/hiyouga/hiyouga"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/capo-cost-aware-prompt-optimization","title":"CAPO: Cost-Aware Prompt Optimization","date":"2025-04-22","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/dual-contrastive-learning-text-classification","title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","date":"2022-01-21","rows_on_this_dataset":1,"code_links":2,"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":"2026-09-24T18:15:14+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/an-empirical-evaluation-of-word-embedding","title":"An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks","date":"2021-04-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/translations-as-additional-contexts-for","title":"Translations as Additional Contexts for Sentence Classification","date":"2018-06-14","rows_on_this_dataset":1,"code_links":1,"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/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":"2026-09-24T18:15:14+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/universal-sentence-encoder","title":"Universal Sentence Encoder","date":"2018-03-29","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+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/learning-to-generate-reviews-and-discovering","title":"Learning to Generate Reviews and Discovering Sentiment","date":"2017-04-05","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"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":"2026-09-24T18:15:14+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."}},{"paper":"/paper/learning-distributed-representations-of","title":"Learning Distributed Representations of Sentences from Unlabelled Data","date":"2016-02-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-adaptive-hierarchical-sentence-model","title":"Self-Adaptive Hierarchical Sentence Model","date":"2015-04-20","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":55,"samples_ran":6,"samples_unverified":49,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"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."}