[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117048-en":3,"doc-seo-117048-105":30,"detail-sidebar-cat-0-en-105":91},{"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},117048,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Predicting Political Leanings With Machine Learning","The study proposes an alternative framework for predicting political sentiment in the United States using machine learning models rather than relying on outdated traditional approaches. It builds ensemble models with features drawn from Google Trends and U.S. Census demographics, aiming for both improved predictive performance and more interpretable insight into electoral dynamics. The research evaluates multiple base classifiers and regressors, combining them through ensemble and delta modeling strategies. Results show high accuracy across training and validation sets, supporting a deeper understanding of political leanings.","PREDICTING POLITICAL LEANINGS WITH MACHINE LEARNING  \nby  \nJay K. Ghosh  \nB. S., University of Colorado at Boulder, 2022  \nA thesis submitted to the  \nFaculty of the Graduate School of the  \nUniversity of Colorado in fulfillment  \nof the requirement for the degree of  \nMaster of Information Science  \nDepartment of Information Science  \n2023  \nCommittee Members:  \nJason Zietz  \nStephen Voida  \nAbram Handler  \nAbstract  \nGhosh, Jay K. (B.S., Information Science, Department of Information Science) Predicting Political Leanings with Machine Learning  \nThesis directed by Professor Jason Zietz  \nThis study proposes an alternative approach to predicting political sentiment in the United States by employing machine learning models. Traditional methods of predicting political sentiment have become outdated and require reevaluation. This work utilizes a variety of features, including Google Trends data and Census demographics, to create ensemble models capable of providing more accurate and insightful predictions of political leanings and electoral outcomes. By leveraging the power of machine learning, this research represents a significant innovation over traditional polling and prediction models. The resulting models achieve high accuracy in both training and validation sets, enabling a deeper understanding of political leanings and insights into their dynamics.  \nTable of Contents  \nCHAPTER 1 ................................................................................................................... 1  \nIntroduction ................................................................................................................... 1  \nLiterature Review .......................................................................................................... 3  \nCHAPTER 2 ................................................................................................................... 8  \nMethods .......................................................................................................................... 8  \nData Collection ........................................................................................................... 8  \nMachine Learning .................................................................................................... 10  \nCHAPTER 3 ................................................................................................................. 12  \nFindings ....................................................................................................................... 12  \nBase Model Classification ........................................................................................ 12  \nGaussian Naive Bayes Classifier.......................................................................... 12  \nSupport Vector Machine Classifier....................................................................... 15  \nLogistic Regression Classifier ............................................................................... 19  \nRandom Forest Classifier ..................................................................................... 23  \nXGBoost Classifier ................................................................................................ 26  \nCatBoost Classifier................................................................................................ 29  \nLightGBM Classifier ............................................................................................. 32  \nEnsemble Model .................................................................................................... 35  \nBase Model Regression............................................................................................. 37  \nSupport Vector Machines Regressor .................................................................... 37  \nElastic Net Regressor ............................................................................................ 39  \nRandom Forest Regressor ...","cbCaidV98DGaOxab","https://ap.wps.com/l/cbCaidV98DGaOxab","pdf",3497313,1,109,"English","en",105,"# Introduction\n## Literature Review\n# Methods\n## Data Collection\n## Machine Learning\n# Findings\n## Base Model Classification\n## Ensemble Model\n## Base Model Regression\n## Delta Model Classification\n## Delta Model Regression","[{\"question\":\"What approach does the thesis use to predict political sentiment?\",\"answer\":\"It uses machine learning models, emphasizing ensemble methods, to predict political sentiment and electoral outcomes rather than relying on traditional polling-style approaches.\"},{\"question\":\"Which data sources support the predictive features?\",\"answer\":\"The study uses features including Google Trends data and U.S. Census demographics to build and evaluate the models.\"},{\"question\":\"How are the predictions generated and evaluated?\",\"answer\":\"Multiple base classifiers and regressors are trained, then combined through ensemble modeling and delta modeling. Performance is reported as high accuracy on both training and validation sets.\"}]","Predicting Political Leanings With Machine Learning | PDF",1785673392,275,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-political-leanings-with-machine-learning","",{"@graph":36,"@context":85},[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/predicting-political-leanings-with-machine-learning/117048/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What approach does the thesis use to predict political sentiment?","Question",{"text":75,"@type":76},"It uses machine learning models, emphasizing ensemble methods, to predict political sentiment and electoral outcomes rather than relying on traditional polling-style approaches.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data sources support the predictive features?",{"text":80,"@type":76},"The study uses features including Google Trends data and U.S. Census demographics to build and evaluate the models.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the predictions generated and evaluated?",{"text":84,"@type":76},"Multiple base classifiers and regressors are trained, then combined through ensemble modeling and delta modeling. Performance is reported as high accuracy on both training and validation sets.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]