{"url":"/dataset/covid-19-fake-news-dataset","name":"COVID-19 Fake News Dataset","full_name":"COVID19 Fake News Detection in English","description_markdown":"Along with COVID-19 pandemic we are also fighting an `infodemic'. Fake news and rumors are rampant on social media. Believing in rumors can cause significant harm. This is further exacerbated at the time of a pandemic. To tackle this, we curate and release a manually annotated dataset of 10,700 social media posts and articles of real and fake news on COVID-19. We benchmark the annotated dataset with four machine learning baselines - Decision Tree, Logistic Regression , Gradient Boost , and Support Vector Machine (SVM). We obtain the best performance of 93.46\\% F1-score with SVM.","description_withheld":null,"homepage":"https://competitions.codalab.org/competitions/26655","introduced_date":"2020-11-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/fighting-an-infodemic-covid-19-fake-news","title":"Fighting an Infodemic: COVID-19 Fake News Dataset","first_author":"Parth Patwa","url":null},"license":{"name":"Custom","url":"https://competitions.codalab.org/competitions/26655"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Fake News Detection","url":"/task/fake-news-detection","datasets_with_task":"/datasets/task/fake-news-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["COVID-19 Fake News Dataset"],"data_loaders":[{"repo":"https://github.com/diptamath/covid_fake_news","url":"https://github.com/diptamath/covid_fake_news","frameworks":["pytorch"]}],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/fake-news-detection-on-covid-19-fake-news","task":"Fake News Detection","dataset_variant":"COVID-19 Fake News Dataset","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"Ensemble Model + Heuristic Post-Processing","paper":"/paper/a-heuristic-driven-ensemble-framework-for","metrics":{"F1":"0.9883"},"code_links":[{"title":"diptamath/covid_fake_news","url":"https://github.com/diptamath/covid_fake_news"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-heuristic-driven-ensemble-framework-for","title":"A Heuristic-driven Ensemble Framework for COVID-19 Fake News Detection","date":"2021-01-10","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."}