{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-stylometric-inquiry-into-hyperpartisan-and","title":"A Stylometric Inquiry into Hyperpartisan and Fake News","arxiv_id":"1702.05638","date":"2017-02-18","proceeding":"ACL 2018 7","authors":["Martin Potthast","Johannes Kiesel","Kevin Reinartz","Janek Bevendorff","Benno Stein"],"abstract":"This paper reports on a writing style analysis of hyperpartisan (i.e.,\nextremely one-sided) news in connection to fake news. It presents a large\ncorpus of 1,627 articles that were manually fact-checked by professional\njournalists from BuzzFeed. The articles originated from 9 well-known political\npublishers, 3 each from the mainstream, the hyperpartisan left-wing, and the\nhyperpartisan right-wing. In sum, the corpus contains 299 fake news, 97% of\nwhich originated from hyperpartisan publishers.\n  We propose and demonstrate a new way of assessing style similarity between\ntext categories via Unmasking---a meta-learning approach originally devised for\nauthorship verification---, revealing that the style of left-wing and\nright-wing news have a lot more in common than any of the two have with the\nmainstream. Furthermore, we show that hyperpartisan news can be discriminated\nwell by its style from the mainstream (F1=0.78), as can be satire from both\n(F1=0.81). Unsurprisingly, style-based fake news detection does not live up to\nscratch (F1=0.46). Nevertheless, the former results are important to implement\npre-screening for fake news detectors.","url_abs":"http://arxiv.org/abs/1702.05638v1","url_pdf":"http://arxiv.org/pdf/1702.05638v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-stylometric-inquiry-into-hyperpartisan-and","repo_url":"https://github.com/webis-de/ACL-18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"authorship-verification","task_name":"Authorship Verification"},{"task_slug":"fake-news-detection","task_name":"Fake News Detection"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[{"slug":"buzzfeed-webis-fake-news-corpus-2016","name":"BuzzFeed-Webis Fake News Corpus 2016","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.05638","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}