{"url":"/dataset/multi-domain-sentiment-dataset-v2-0","name":"Multi-Domain Sentiment","full_name":null,"description_markdown":"The Multi-Domain Sentiment Dataset contains product reviews taken from Amazon.com from many product types (domains). Some domains (books and dvds) have hundreds of thousands of reviews. Others (musical instruments) have only a few hundred. Reviews contain star ratings (1 to 5 stars) that can be converted into binary labels if needed.\r\n\r\nSource: [Multi-Domain Sentiment Dataset (version 2.0)](https://www.cs.jhu.edu/~mdredze/datasets/sentiment/)","description_withheld":null,"homepage":"https://www.cs.jhu.edu/~mdredze/datasets/sentiment/","introduced_date":"2007-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/biographies-bollywood-boom-boxes-and-blenders","title":"Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification","first_author":"John Blitzer","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Multi-Domain Sentiment Dataset","Multi-Domain Sentiment"],"data_loaders":[],"num_papers_in_archive":54,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-multi-domain-sentiment","task":"Sentiment Analysis","dataset_variant":"Multi-Domain Sentiment Dataset","rows":6,"metrics":["DVD","Books","Electronics","Kitchen","Average"],"first_row_in_archive_order":{"model":"UDALM: Unsupervised Domain Adaptation through Language Modeling","paper":"/paper/udalm-unsupervised-domain-adaptation-through","metrics":{"Average":"91.74","Books":"90.63","DVD":"89.78","Electronics":"92.78","Kitchen":"93.77"},"code_links":[{"title":"ckarouzos/slp_daptmlm","url":"https://github.com/ckarouzos/slp_daptmlm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/udalm-unsupervised-domain-adaptation-through","title":"UDALM: Unsupervised Domain Adaptation through Language Modeling","date":"2021-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-distributional-correspondence","title":"Revisiting Distributional Correspondence Indexing: A Python Reimplementation and New Experiments","date":"2018-10-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/strong-baselines-for-neural-semi-supervised","title":"Strong Baselines for Neural Semi-supervised Learning under Domain Shift","date":"2018-04-25","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/asymmetric-tri-training-for-unsupervised","title":"Asymmetric Tri-training for Unsupervised Domain Adaptation","date":"2017-02-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-variational-fair-autoencoder","title":"The Variational Fair Autoencoder","date":"2015-11-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/domain-adversarial-training-of-neural","title":"Domain-Adversarial Training of Neural Networks","date":"2015-05-28","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":52,"samples_ran":33,"samples_unverified":19,"pointer_only_for_licence":22,"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":2,"samples_harvested":57,"samples_ran":33,"samples_unverified":24,"pointer_only_for_licence":22,"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."}