{"url":"/dataset/shaj","name":"SHAJ","full_name":"Spoken Hate in the Albanian Jargon","description_markdown":"This is an abusive/offensive language detection dataset for Albanian. The data is formatted following the OffensEval convention. Data is from Instagram and YouTube comments.","description_withheld":null,"homepage":"https://stromberg.ai/publication/albanian/","introduced_date":"2021-07-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/detecting-abusive-albanian","title":"Detecting Abusive Albanian","first_author":"Erida Nurce","url":null},"license":{"name":"CC-BY 4.0","url":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":"Albanian","url":"/datasets/language/albanian"}],"variants":["SHAJ"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/strombergnlp/shaj","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hate-speech-detection-on-shaj","task":"Hate Speech Detection","dataset_variant":"SHAJ","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"Baseline BERT (task A)","paper":"/paper/detecting-abusive-albanian","metrics":{"F1":"0.77"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/detecting-abusive-albanian","title":"Detecting Abusive Albanian","date":"2021-07-28","rows_on_this_dataset":1,"code_links":0,"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."}