{"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/analyzing-polarization-in-social-media-method","title":"Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings","arxiv_id":"1904.01596","date":"2019-04-02","proceeding":"NAACL 2019 6","authors":["Dorottya Demszky","Nikhil Garg","Rob Voigt","James Zou","Matthew Gentzkow","Jesse Shapiro","Dan Jurafsky"],"abstract":"We provide an NLP framework to uncover four linguistic dimensions of\npolitical polarization in social media: topic choice, framing, affect and\nillocutionary force. We quantify these aspects with existing lexical methods,\nand propose clustering of tweet embeddings as a means to identify salient\ntopics for analysis across events; human evaluations show that our approach\ngenerates more cohesive topics than traditional LDA-based models. We apply our\nmethods to study 4.4M tweets on 21 mass shootings. We provide evidence that the\ndiscussion of these events is highly polarized politically and that this\npolarization is primarily driven by partisan differences in framing rather than\ntopic choice. We identify framing devices, such as grounding and the\ncontrasting use of the terms \"terrorist\" and \"crazy\", that contribute to\npolarization. Results pertaining to topic choice, affect and illocutionary\nforce suggest that Republicans focus more on the shooter and event-specific\nfacts (news) while Democrats focus more on the victims and call for policy\nchanges. Our work contributes to a deeper understanding of the way group\ndivisions manifest in language and to computational methods for studying them.","url_abs":"http://arxiv.org/abs/1904.01596v2","url_pdf":"http://arxiv.org/pdf/1904.01596v2.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":"analyzing-polarization-in-social-media-method","repo_url":"https://github.com/ddemszky/framing-twitter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01596","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}