{"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/politics-pretraining-with-same-story-article-1","title":"POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection","arxiv_id":"2205.00619","date":"2022-05-02","proceeding":"Findings (NAACL) 2022 7","authors":["Yujian Liu","Xinliang Frederick Zhang","David Wegsman","Nick Beauchamp","Lu Wang"],"abstract":"Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology prediction and stance detection tasks. Further analyses show that POLITICS is especially good at understanding long or formally written texts, and is also robust in few-shot learning scenarios.","url_abs":"https://arxiv.org/abs/2205.00619v1","url_pdf":"https://arxiv.org/pdf/2205.00619v1.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":"politics-pretraining-with-same-story-article-1","repo_url":"https://github.com/launchnlp/politics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"politics-pretraining-with-same-story-article-1","repo_url":"https://github.com/lyh6560new/p3sum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"stance-detection","task_name":"Stance Detection"}],"methods":[],"datasets_introduced":[{"slug":"bignews","name":"BigNews","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.00619","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}