{"url":"/dataset/illness-dataset","name":"Illness-dataset","full_name":"Illness multi-domain textual dataset","description_markdown":"A dataset for evaluating text classification, domain adaptation, and active learning models. The dataset consists of 22,660 documents (tweets) collected in 2018 and 2019. It spans across four domains: Alzheimer's, Parkinson's, Cancer, and Diabetes.","description_withheld":null,"homepage":"https://github.com/p-karisani/illness-dataset","introduced_date":"2021-12-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/contextual-multi-view-query-learning-for","title":"Multi-View Active Learning for Short Text Classification in User-Generated Data","first_author":"Payam Karisani","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Active Learning","url":"/task/active-learning","datasets_with_task":"/datasets/task/active-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Illness-dataset"],"data_loaders":[],"num_papers_in_archive":5,"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":"2026-09-25T09:33:49+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."}