{"url":"/dataset/beeradvocate","name":"BeerAdvocate","full_name":null,"description_markdown":"BeerAdvocate is a dataset that consists of beer reviews from beeradvocate. The data span a period of more than 10 years, including all ~1.5 million reviews up to November 2011. Each review includes ratings in terms of five \"aspects\": appearance, aroma, palate, taste, and overall impression. Reviews include product and user information, followed by each of these five ratings, and a plaintext review.\r\n\r\nSource: [https://snap.stanford.edu/data/web-BeerAdvocate.html](https://snap.stanford.edu/data/web-BeerAdvocate.html)","description_withheld":null,"homepage":"https://snap.stanford.edu/data/web-BeerAdvocate.html","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-amateurs-to-connoisseurs-modeling-the","title":"From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews","first_author":"Julian McAuley","url":null},"license":null,"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Recommendation Systems","url":"/task/recommendation-systems","datasets_with_task":"/datasets/task/recommendation-systems"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BeerAdvocate"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/recommendation-systems-on-beeradvocate","task":"Recommendation Systems","dataset_variant":"BeerAdvocate","rows":1,"metrics":["MAE","RMSE"],"first_row_in_archive_order":{"model":"CFM","paper":"/paper/predicting-ratings-in-multi-criteria","metrics":{"MAE":"0.5833","RMSE":"0.5833"},"code_links":[{"title":"LucaM1985/CFM","url":"https://github.com/LucaM1985/CFM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/predicting-ratings-in-multi-criteria","title":"Predicting ratings in multi-criteria recommender systems via a collective factor model","date":"2021-05-21","rows_on_this_dataset":1,"code_links":1,"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."}