{"url":"/dataset/dataset-of-propaganda-techniques-of-the-state","name":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","full_name":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","description_markdown":"This data is for the Mis2-KDD 2021 under review paper: Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People’s Republic of China\r\n\r\nWe present our dataset that focuses on propaganda techniques in Mandarin based on a state-linked information operations dataset from the PRC released by Twitter in July 2019. The dataset consists of multi-label propaganda techniques of the sampled tweets.\r\n\r\nIn total, we have 9,950 labeled tweets with 21 different propaganda techniques. The tweets are the state-linked information operations dataset from the PRC released by Twitter.","description_withheld":null,"homepage":"https://github.com/annabechang/Propaganda_Tech_Twitter_PRC","introduced_date":"2021-06-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/dataset-of-propaganda-techniques-of-the-state","title":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","first_author":"Rong-Ching Chang","url":null},"license":{"name":"CC BY-NC-SA","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multi-Label Classification","url":"/task/multi-label-classification","datasets_with_task":"/datasets/task/multi-label-classification"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Propaganda technique identification","url":"/task/propaganda-technique-identification","datasets_with_task":"/datasets/task/propaganda-technique-identification"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China"],"data_loaders":[{"repo":"https://github.com/annabechang/Propaganda_Tech_Twitter_PRC","url":"https://github.com/annabechang/Propaganda_Tech_Twitter_PRC","frameworks":["pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-text-classification-on-dataset-of","task":"Multi-Label Text Classification","dataset_variant":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","rows":1,"metrics":["1:1 Accuracy","F1 - macro","Micro F1"],"first_row_in_archive_order":{"model":"Bert","paper":"/paper/dataset-of-propaganda-techniques-of-the-state","metrics":{"1:1 Accuracy":"0.80352","F1 - macro":"0.20803","Micro F1":"0.85431"},"code_links":[{"title":"annabechang/Propaganda_Tech_Twitter_PRC","url":"https://github.com/annabechang/Propaganda_Tech_Twitter_PRC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dataset-of-propaganda-techniques-of-the-state","title":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","date":"2021-06-14","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."}