{"url":"/dataset/twitter-death-hoaxes","name":"Twitter Death Hoaxes","full_name":null,"description_markdown":"This is a dataset for detection fake death hoaxes. It consists of of death reports collected from Twitter between 1st January, 2012 and 31st December, 2014. It was collected by tracking the keyword 'RIP', and matching those tweets in which a name is mentioned next to RIP. Matching names were identified by using Wikidata as a database of names. \r\n\r\nThe dataset contains 4,007 death reports, of which 2,301 are real deaths, 1,092 are commemorations and 614 are fake deaths.\r\n\r\nSource: [Early Detection of Social Media Hoaxes at Scale](https://arxiv.org/abs/1801.07311)","description_withheld":null,"homepage":"https://figshare.com/articles/dataset/Twitter_Death_Hoaxes_dataset/5688811","introduced_date":"2018-01-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-class-specific-word-representations","title":"Early Detection of Social Media Hoaxes at Scale","first_author":"Arkaitz Zubiaga","url":null},"license":null,"modalities":[],"tasks":[{"name":"Veracity Classification","url":"/task/veracity-classification","datasets_with_task":"/datasets/task/veracity-classification"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[],"variants":["Twitter Death Hoaxes"],"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."}