{"url":"/dataset/wikidetox","name":"WikiDetox","full_name":"Wikipedia Detox","description_markdown":"An annotated dataset of 1m crowd-sourced annotations that cover 100k talk page diffs (with 10 judgements per diff) for personal attacks, aggression, and toxicity.","description_withheld":null,"homepage":"https://github.com/ewulczyn/wiki-detox","introduced_date":"2016-10-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/ex-machina-personal-attacks-seen-at-scale","title":"Ex Machina: Personal Attacks Seen at Scale","first_author":"Ellery Wulczyn","url":null},"license":{"name":"Apache License, Version 2.0","url":"https://github.com/ewulczyn/wiki-detox/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Toxic Comment Classification","url":"/task/toxic-comment-classification","datasets_with_task":"/datasets/task/toxic-comment-classification"},{"name":"Aggression Identification","url":"/task/aggression-identification","datasets_with_task":"/datasets/task/aggression-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiDetox"],"data_loaders":[],"num_papers_in_archive":7,"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."}