{"url":"/dataset/caves","name":"CAVES","full_name":"A Dataset to facilitate Explainable Classification and Summarization of Concerns towards COVID Vaccines","description_markdown":"**CAVES** is the first large-scale dataset containing about 10k COVID-19 anti-vaccine tweets labelled into various specific anti-vaccine concerns in a multi-label setting. This is also the first multi-label classification dataset that provides explanations for each of the labels. Additionally, the dataset also provides class-wise summaries of all the tweets.","description_withheld":null,"homepage":"https://github.com/sohampoddar26/caves-data","introduced_date":"2022-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/caves-a-dataset-to-facilitate-explainable","title":"CAVES: A Dataset to facilitate Explainable Classification and Summarization of Concerns towards COVID Vaccines","first_author":"Soham Poddar","url":null},"license":{"name":"GPL-3.0","url":"https://github.com/sohampoddar26/caves-data/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multi-Label Classification","url":"/task/multi-label-classification","datasets_with_task":"/datasets/task/multi-label-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CAVES"],"data_loaders":[],"num_papers_in_archive":2,"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."}