[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125663-en":3,"doc-seo-125663-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125663,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Using Machine Learning to Measure Political Polarization on Social Media","The project examines how political polarization in the United States can be quantified using publicly available social media discourse. It addresses the lack of a single agreed definition of polarization and proposes a conceptual breakdown into style, purpose, and mindset. Using text mining and natural language processing, the work builds a classification approach to distinguish polarized from non-polarized content, leveraging labeled data and generalizing to unlabeled posts for measuring change over time.","University of Mary Washington  \nEagle Scholar  \nStudent Research Submissions  \nSpring 4-28-2023  \nUsing Machine Learning to Measure Political Polarization on Social Media  \nVeronica Cagle  \nFollow this and additional works at: [https://scholar.umw.edu/student_research](https://scholar.umw.edu/student_research)  \n Part of the Data Science Commons  \nRecommended Citation  \nCagle, Veronica, \"Using Machine Learning to Measure Political Polarization on Social Media\" (2023) . Student Research Submissions. 507.  \n[https://scholar.umw.edu/student_research/507](https://scholar.umw.edu/student_research/507)  \nThis Honors Project is brought to you for free and open access by Eagle Scholar. It has been accepted for inclusion in Student Research Submissions by an authorized administrator of Eagle Scholar. For more information, please contact [archives@umw.edu](archives@umw.edu).  \nUsing Machine Learning to Measure Political Polarization on Social Media  \nVeronica Cagle  \nUniversity of Mary Washington  \nIntroduction  \nThere have been a lot of discussions regarding U.S. politics that the country is becoming more politically polarized[8,15,23]. There is a lot of disagreement over the topic of political polarization. Depending on what group is being measured can also impact expert opinions. We can look at the public[14] or we can look at party elites[25]. There is the potential for political polarization in many different groups of people. I focused on the public and if we as a society have become more polarized over the years. Some claim that we have, especially considering political events in the past few years while others disagree[1] . Polarization creates a divide between us and makes it difficult for us as a society to reach a consensus. In a democracy, it is important for us to come together to make a decision that benefits everyone.  \nWith an increase in social media sites for information to spread and the public being able to communicate more freely with each other, there is a way for polarization to be measured[2] . Online discourse is increasingly important and openly available for researchers, or anyone interested, to look into. Social media should reflect some of the public’s opinions and allows for the ability to measure the degree to which polarization has changed or stayed the same[27] .  \nPolarization itself is a very nuanced topic. For me to be able to understand political polarization, I had to perform a Literature Search. This entails a search of published work to find similar research to what I am interested in. I needed to see the work that had already been done, so I could separate myself and have a unique finding to present. I spent a good amount of time reading about political polarization and how to measure it[13,18,22] . As I read through many papers, I realized that thereis not a simple agreed-upon definition for polarization. I, along with three other researchers on my team, came together to discuss our definition of polarization. I took into consideration the papers that I had read as well as my own idea ofwhat I thought polarization meant. We spent a lot of time discussing our own definitions before deciding on our definition. We landed on the idea that polarization can be broken down into style, purpose, and mindset. The style can be described as combative, while the purpose is to win an argument, and the mindset is stubborn. On the opposite side, not polarized has a calm style with the purpose of learning and forming opinions and keeping an open mind. Because polarization is such a complex topic, this was the best attempt at creating a definition that I could have in my mind when reading through public thought.  \nAs mentioned earlier, social media has increased the data that is available. This data is most often text data that users have typed and posted on a website[7,13,22]. To go through all of this data, I went through the process of text mining[29] . This is a way of examining large amounts of text and find","cbCaifzGotJs4RiE","https://ap.wps.com/l/cbCaifzGotJs4RiE","pdf",418994,1,11,"English","en",105,"# Introduction\n## Measuring political polarization with social media\n## Defining polarization\n## Text mining and natural language processing\n## Classification approach\n# Dataset & Preprocessing","[{\"question\":\"What modeling approach is used to detect whether text is polarized?\",\"answer\":\"The work formulates polarization detection as a classification task, training on labeled examples and then applying the model to unlabeled text to predict polarized versus non-polarized content.\"}]","Using Machine Learning to Measure Political Polarization on Social Media | PDF",1785900508,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"using-machine-learning-to-measure-political-polarization-on-social-media","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/using-machine-learning-to-measure-political-polarization-on-social-media/125663/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What modeling approach is used to detect whether text is polarized?","Question",{"text":75,"@type":76},"The work formulates polarization detection as a classification task, training on labeled examples and then applying the model to unlabeled text to predict polarized versus non-polarized content.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]