{"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/learning-hierarchical-discourse-level","title":"Learning Hierarchical Discourse-level Structure for Fake News Detection","arxiv_id":"1903.07389","date":"2019-02-27","proceeding":"NAACL 2019 6","authors":["Hamid Karimi","Jiliang Tang"],"abstract":"On the one hand, nowadays, fake news articles are easily propagated through\nvarious online media platforms and have become a grand threat to the\ntrustworthiness of information. On the other hand, our understanding of the\nlanguage of fake news is still minimal. Incorporating hierarchical\ndiscourse-level structure of fake and real news articles is one crucial step\ntoward a better understanding of how these articles are structured.\nNevertheless, this has rarely been investigated in the fake news detection\ndomain and faces tremendous challenges. First, existing methods for capturing\ndiscourse-level structure rely on annotated corpora which are not available for\nfake news datasets. Second, how to extract out useful information from such\ndiscovered structures is another challenge. To address these challenges, we\npropose Hierarchical Discourse-level Structure for Fake news detection. HDSF\nlearns and constructs a discourse-level structure for fake/real news articles\nin an automated and data-driven manner. Moreover, we identify insightful\nstructure-related properties, which can explain the discovered structures and\nboost our understating of fake news. Conducted experiments show the\neffectiveness of the proposed approach. Further structural analysis suggests\nthat real and fake news present substantial differences in the hierarchical\ndiscourse-level structures.","url_abs":"http://arxiv.org/abs/1903.07389v6","url_pdf":"http://arxiv.org/pdf/1903.07389v6.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":"learning-hierarchical-discourse-level","repo_url":"https://github.com/hamidkarimi/DHSF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-hierarchical-discourse-level","repo_url":"https://github.com/hamidkarimi/HDSF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"fake-news-detection","task_name":"Fake News Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.07389","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}