{"url":"/dataset/blog-authorship-corpus","name":"Blog Authorship Corpus","full_name":null,"description_markdown":"The Blog Authorship Corpus consists of the collected posts of 19,320 bloggers gathered from blogger.com in August 2004. The corpus incorporates a total of 681,288 posts and over 140 million words - or approximately 35 posts and 7250 words per person.  \r\n\r\nSource: [Blog Authorship Corpus](https://u.cs.biu.ac.il/~koppel/BlogCorpus.htm)","description_withheld":null,"homepage":"https://u.cs.biu.ac.il/~koppel/BlogCorpus.htm","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Authorship Verification","url":"/task/authorship-verification","datasets_with_task":"/datasets/task/authorship-verification"}],"languages":[],"variants":["Blog Authorship Corpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/barilan/blog_authorship_corpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/blog_authorship_corpus","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":2,"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."}