{"url":"/dataset/hate-speech","name":"Hate Speech","full_name":null,"description_markdown":"Dataset of hate speech annotated on Internet forum posts in English at sentence-level. The source forum in Stormfront, a large online community of white nacionalists. A total of 10,568 sentence have been been extracted from Stormfront and classified as conveying hate speech or not.\r\n\r\nSource: [https://arxiv.org/pdf/1809.04444.pdf](https://arxiv.org/pdf/1809.04444.pdf)","description_withheld":null,"homepage":"https://github.com/aitor-garcia-p/hate-speech-dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/hate-speech-dataset-from-a-white-supremacy","title":"Hate Speech Dataset from a White Supremacy Forum","first_author":"Ona de Gibert","url":null},"license":{"name":"CC BY-SA 3.0 ES","url":"https://creativecommons.org/licenses/by-sa/3.0/es/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Hate Speech Detection","url":"/task/hate-speech-detection","datasets_with_task":"/datasets/task/hate-speech-detection"},{"name":"Abusive Language","url":"/task/abusive-language","datasets_with_task":"/datasets/task/abusive-language"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Hate Speech","hate_speech18"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/odegiber/hate_speech18","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/5roop/FRENK-hate-hr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hate_speech18","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/aitor-garcia-p/hate-speech-dataset","url":"https://github.com/aitor-garcia-p/hate-speech-dataset","frameworks":[]}],"num_papers_in_archive":180,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-hate-speech18","task":"Text Classification","dataset_variant":"hate_speech18","rows":0,"metrics":["Accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"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."}