{"url":"/dataset/prachathai-67k","name":"prachathai-67k","full_name":null,"description_markdown":"The prachathai-67k dataset was scraped from the news site Prachathai excluding articles with less than 500 characters of body text (mostly images and cartoons). It contains 67,889 articles with 51,797 tags from August 24, 2004 to November 15, 2018.\r\n\r\nSource: [prachathai-67k](https://github.com/PyThaiNLP/prachathai-67k/)","description_withheld":null,"homepage":"https://github.com/PyThaiNLP/prachathai-67k/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["prachathai-67k"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PyThaiNLP/prachathai67k","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/prachathai67k","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Kaggle/kaggle-api","url":"https://www.kaggle.com/datasets/ratthachat/pythainlp-prachatai-67k","frameworks":[]},{"repo":"https://github.com/PyThaiNLP/prachathai-67k","url":"https://github.com/PyThaiNLP/prachathai-67k","frameworks":[]}],"num_papers_in_archive":0,"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."}