{"url":"/dataset/arsarcasm","name":"ArSarcasm","full_name":null,"description_markdown":"ArSarcasm is a new Arabic sarcasm detection dataset. The dataset was created using previously available Arabic sentiment analysis datasets (SemEval 2017 and ASTD) and adds sarcasm and dialect labels to them. The dataset contains 10,547 tweets, 1,682 (16%) of which are sarcastic.","description_withheld":null,"homepage":"https://github.com/iabufarha/ArSarcasm","introduced_date":"2020-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-arabic-sentiment-analysis-to-sarcasm","title":"From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset","first_author":"Ibrahim Abu Farha","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"},{"name":"Sarcasm Detection","url":"/task/sarcasm-detection","datasets_with_task":"/datasets/task/sarcasm-detection"},{"name":"Dialect Identification","url":"/task/dialect-identification","datasets_with_task":"/datasets/task/dialect-identification"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["ArSarcasm"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}