{"url":"/dataset/sarcasm-corpus-v2","name":"Sarcasm Corpus V2","full_name":null,"description_markdown":"The Sarcasm Corpus contains sarcastic and non-sarcastic utterances of three different types, which are balanced with half of the samples being sarcastic and half non-sarcastic.\r\nThe three types are:\r\n\r\n* Generic: 6,520 samples\r\n* Rhetorical Questions: 1,702 samples\r\n* Hyperbole: 1,164 samples\r\n\r\nSource: [Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue](https://arxiv.org/pdf/1709.05404.pdf)","description_withheld":null,"homepage":"https://nlds.soe.ucsc.edu/sarcasm2","introduced_date":"2017-09-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/creating-and-characterizing-a-diverse-corpus","title":"Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue","first_author":"Shereen Oraby","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Sarcasm Detection","url":"/task/sarcasm-detection","datasets_with_task":"/datasets/task/sarcasm-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Sarcasm Corpus V2"],"data_loaders":[{"repo":null,"url":"","frameworks":["tf","pytorch"]}],"num_papers_in_archive":5,"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."}