{"url":"/dataset/stanceosaurus","name":"Stanceosaurus","full_name":null,"description_markdown":"**Stanceosaurus** is a corpus of 28,033 tweets in English, Hindi, and Arabic annotated with stance towards 251 misinformation claims. The claims in Stanceosaurus originate from 15 fact-checking sources that cover diverse geographical regions and cultures. Unlike existing stance datasets, it introduces a more fine-grained 5-class labeling strategy with additional subcategories to distinguish implicit stance.\r\n\r\nSource: [Stanceosaurus: Classifying Stance Towards Multilingual Misinformation](https://arxiv.aorg/pdf/2210.15954v1.pdf)\r\n\r\nImage Source: [https://arxiv.aorg/pdf/2210.15954v1.pdf](https://arxiv.aorg/pdf/2210.15954v1.pdf)","description_withheld":null,"homepage":"https://github.com/JonathanQZheng/Stanceosaurus/","introduced_date":"2022-10-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/stanceosaurus-classifying-stance-towards","title":"Stanceosaurus: Classifying Stance Towards Multilingual Misinformation","first_author":"Jonathan Zheng","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Fact Checking","url":"/task/fact-checking","datasets_with_task":"/datasets/task/fact-checking"},{"name":"Misinformation","url":"/task/misinformation","datasets_with_task":"/datasets/task/misinformation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["Stanceosaurus"],"data_loaders":[],"num_papers_in_archive":3,"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."}