{"url":"/dataset/toxic-comment-classification-challenge","name":"Jigsaw Toxic Comment Classification Dataset","full_name":null,"description_markdown":"You are provided with a large number of Wikipedia comments which have been labeled by human raters for toxic behavior. The types of toxicity are:\r\n\r\ntoxic\r\nsevere_toxic\r\nobscene\r\nthreat\r\ninsult\r\nidentity_hate\r\nYou must create a model which predicts a probability of each type of toxicity for each comment.\r\n\r\nFile descriptions\r\ntrain.csv - the training set, contains comments with their binary labels\r\ntest.csv - the test set, you must predict the toxicity probabilities for these comments. To deter hand labeling, the test set contains some comments which are not included in scoring.\r\nsample_submission.csv - a sample submission file in the correct format\r\ntest_labels.csv - labels for the test data; value of -1 indicates it was not used for scoring; (Note: file added after competition close!)\r\nUsage\r\nThe dataset under CC0, with the underlying comment text being governed by Wikipedia's CC-SA-3.0","description_withheld":null,"homepage":"https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Wikipedia's CC-SA-3.0","url":"https://creativecommons.org/licenses/by-sa/3.0/"},"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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Jigsaw Toxic Comment Classification Dataset"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/toxic-comment-classification-on-jigsaw-toxic","task":"Toxic Comment Classification","dataset_variant":"Jigsaw Toxic Comment Classification Dataset","rows":1,"metrics":["Validation Accuracy"],"first_row_in_archive_order":{"model":"CapsNet","paper":"/paper/evaluating-the-effectiveness-of-capsule","metrics":{"Validation Accuracy":"90.44"},"code_links":[{"title":"TashinAhmed/HATE","url":"https://github.com/TashinAhmed/HATE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/evaluating-the-effectiveness-of-capsule","title":"Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings","date":"2023-10-12","rows_on_this_dataset":1,"code_links":1,"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."}