{"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/debunking-fake-news-one-feature-at-a-time","title":"Debunking Fake News One Feature at a Time","arxiv_id":"1808.02831","date":"2018-08-08","proceeding":null,"authors":["Melanie Tosik","Antonio Mallia","Kedar Gangopadhyay"],"abstract":"Identifying the stance of a news article body with respect to a certain\nheadline is the first step to automated fake news detection. In this paper, we\nintroduce a 2-stage ensemble model to solve the stance detection task. By using\nonly hand-crafted features as input to a gradient boosting classifier, we are\nable to achieve a score of 9161.5 out of 11651.25 (78.63%) on the official Fake\nNews Challenge (Stage 1) dataset. We identify the most useful features for\ndetecting fake news and discuss how sampling techniques can be used to improve\nrecall accuracy on a highly imbalanced dataset.","url_abs":"http://arxiv.org/abs/1808.02831v1","url_pdf":"http://arxiv.org/pdf/1808.02831v1.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":"debunking-fake-news-one-feature-at-a-time","repo_url":"https://github.com/NYU-FNC/FakeNewsChallenge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"fake-news-detection","task_name":"Fake News Detection"},{"task_slug":"stance-detection","task_name":"Stance Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}