{"url":"/dataset/smokeng","name":"SmokEng","full_name":null,"description_markdown":"SmokEng is a dataset of 3144 tweets, which are selected based on the presence of colloquial slang related to smoking and analyze it based on the semantics of the tweet. \r\n\r\nSource: [SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text](/paper/smokeng-towards-fine-grained-classification)","description_withheld":null,"homepage":"https://github.com/kartikeypant/smokeng-tobacco-classification","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/smokeng-towards-fine-grained-classification","title":"SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text","first_author":"Kartikey Pant","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Multi-class Classification","url":"/task/multi-class-classification","datasets_with_task":"/datasets/task/multi-class-classification"}],"languages":[],"variants":["SmokEng"],"data_loaders":[{"repo":"https://github.com/kartikeypant/smokeng-tobacco-classification","url":"https://github.com/kartikeypant/smokeng-tobacco-classification","frameworks":[]}],"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."}