{"url":"/dataset/rushold","name":"RUSHOLD","full_name":"Roman Urdu Hate Speech and Offensive Language Dataset","description_markdown":"RUHSOLD is hate speech and offensive language dataset in Roman Urdu. The dataset contains over 10 thousand tweets that are hand labelled into the following categories:\r\n1) Abusive/Offensive\r\n2) Untargeted\r\n3) Sexism\r\n4) Religious\r\n5) Neutral","description_withheld":null,"homepage":"https://github.com/haroonshakeel/roman_urdu_hate_speech","introduced_date":"2020-11-30","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[{"name":"Urdu","url":"/datasets/language/urdu"}],"variants":["RUSHOLD"],"data_loaders":[{"repo":"https://github.com/haroonshakeel/roman_urdu_hate_speech","url":"https://github.com/haroonshakeel/roman_urdu_hate_speech","frameworks":[]}],"num_papers_in_archive":1,"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":"2026-09-24T18:15:14+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."}