{"url":"/dataset/told-br","name":"ToLD-Br","full_name":"Toxic Language Detection for Brazilian Portuguese","description_markdown":"The **Toxic Language Detection for Brazilian Portuguese** (**ToLD-Br**) is a dataset with tweets in Brazilian Portuguese annotated according to different toxic aspects.\n\nSource: [https://github.com/JAugusto97/ToLD-Br](https://github.com/JAugusto97/ToLD-Br)","description_withheld":null,"homepage":"https://github.com/JAugusto97/ToLD-Br","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/toxic-language-detection-in-social-media-for","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","first_author":"João A. Leite","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Hate Speech Detection","url":"/task/hate-speech-detection","datasets_with_task":"/datasets/task/hate-speech-detection"}],"languages":[{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["ToLD-Br"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/JAugusto97/told-br","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/told-br","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/JAugusto97/ToLD-Br","url":"https://github.com/JAugusto97/ToLD-Br","frameworks":[]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hate-speech-detection-on-told-br","task":"Hate Speech Detection","dataset_variant":"ToLD-Br","rows":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Multilingual BERT","paper":"/paper/toxic-language-detection-in-social-media-for","metrics":{"F1-score":"0.75"},"code_links":[{"title":"JAugusto97/ToLD-Br","url":"https://github.com/JAugusto97/ToLD-Br"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/toxic-language-detection-in-social-media-for","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","date":"2020-10-09","rows_on_this_dataset":2,"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."}