{"url":"/dataset/labr","name":"LABR","full_name":"Large-Scale Arabic Book Reviews","description_markdown":"LABR is a large sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars. \r\n\r\nSource: [LABR: A Large Scale Arabic Book Reviews Dataset](https://www.aclweb.org/anthology/P13-2088)","description_withheld":null,"homepage":"https://github.com/mohamedadaly/LABR","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/labr-a-large-scale-arabic-book-reviews","title":"LABR: A Large Scale Arabic Book Reviews Dataset","first_author":"Mohamed Aly","url":null},"license":{"name":"Custom","url":"https://github.com/mohamedadaly/LABR"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Arabic Sentiment Analysis","url":"/task/arabic-sentiment-analysis","datasets_with_task":"/datasets/task/arabic-sentiment-analysis"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["LABR (2-class, unbalanced)","LABR"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mohamedadaly/labr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/labr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/mohamedadaly/LABR","url":"https://github.com/mohamedadaly/LABR","frameworks":[]}],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-labr-2-class-unbalanced-1","task":"Sentiment Analysis","dataset_variant":"LABR (2-class, unbalanced)","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"AraBERTv1","paper":"/paper/arabert-transformer-based-model-for-arabic","metrics":{"Accuracy":"86.7"},"code_links":[{"title":"aub-mind/araBERT","url":"https://github.com/aub-mind/araBERT"},{"title":"issam9/finetuning-bert-models-for-arabic-dialect-detection","url":"https://github.com/issam9/finetuning-bert-models-for-arabic-dialect-detection"},{"title":"mramly/CairoMent","url":"https://github.com/mramly/CairoMent"},{"title":"msfasha/Arabic-NLP","url":"https://github.com/msfasha/Arabic-NLP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}