{"url":"/dataset/one-million-posts-corpus","name":"One Million Posts Corpus","full_name":null,"description_markdown":"An annotated data set consisting of user comments posted to an Austrian newspaper website (in German language).\r\n\r\nDER STANDARD is an Austrian daily broadsheet newspaper. On the newspaper’s website, there is a discussion section below each news article where readers engage in online discussions. The data set contains a selection of user posts from the 12 month time span from 2015-06-01 to 2016-05-31. There are 11,773 labeled and 1,000,000 unlabeled posts in the data set. The labeled posts were annotated by professional forum moderators employed by the newspaper.\r\n\r\nSource: [One Million Posts Corpus](https://ofai.github.io/million-post-corpus/)","description_withheld":null,"homepage":"https://ofai.github.io/million-post-corpus/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["One Million Posts Corpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/OFAI/omp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/omp","frameworks":["tf","pytorch","jax"]}],"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."}