{"url":"/dataset/nela-gt-2021","name":"NELA-GT-2021","full_name":null,"description_markdown":"**NELA-GT-2021** is the fourth installment of the NELA-GT datasets, NELA-GT-2021. The dataset contains 1.8M articles from 367 outlets between January 1st, 2021 and December 31st, 2021. Just as in past releases of the dataset, NELA-GT-2021 includes outlet-level veracity labels from Media Bias/Fact Check and tweets embedded in collected news articles.","description_withheld":null,"homepage":"https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/RBKVBM","introduced_date":"2022-03-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/nela-gt-2021-a-large-multi-labelled-news","title":"NELA-GT-2022: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles","first_author":"Maurício Gruppi","url":null},"license":{"name":"CC0","url":"https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/RBKVBM"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Misinformation","url":"/task/misinformation","datasets_with_task":"/datasets/task/misinformation"}],"languages":[],"variants":["NELA-GT-2021"],"data_loaders":[],"num_papers_in_archive":1,"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."}