{"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/discovering-political-topics-in-facebook","title":"Discovering Political Topics in Facebook Discussion threads with Graph Contextualization","arxiv_id":"1708.06872","date":"2017-08-23","proceeding":null,"authors":["Yilin Zhang","Marie Poux-Berthe","Chris Wells","Karolina Koc-Michalska","Karl Rohe"],"abstract":"We propose a graph contextualization method, pairGraphText, to study\npolitical engagement on Facebook during the 2012 French presidential election.\nIt is a spectral algorithm that contextualizes graph data with text data for\nonline discussion thread. In particular, we examine the Facebook posts of the\neight leading candidates and the comments beneath these posts. We find evidence\nof both (i) candidate-centered structure, where citizens primarily comment on\nthe wall of one candidate and (ii) issue-centered structure (i.e. on political\ntopics), where citizens' attention and expression is primarily directed towards\na specific set of issues (e.g. economics, immigration, etc). To identify\nissue-centered structure, we develop pairGraphText, to analyze a network with\nhigh-dimensional features on the interactions (i.e. text). This technique\nscales to hundreds of thousands of nodes and thousands of unique words. In the\nFacebook data, spectral clustering without the contextualizing text information\nfinds a mixture of (i) candidate and (ii) issue clusters. The contextualized\ninformation with text data helps to separate these two structures. We conclude\nby showing that the novel methodology is consistent under a statistical model.","url_abs":"http://arxiv.org/abs/1708.06872v3","url_pdf":"http://arxiv.org/pdf/1708.06872v3.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":"discovering-political-topics-in-facebook","repo_url":"https://github.com/yzhang672/AOAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"discovering-political-topics-in-facebook","repo_url":"https://github.com/yzhang672/Spectral-Contextualization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[{"method_slug":"spectral-clustering","method_name":"Spectral Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}