Date of Submission
Spring 2019
Academic Programs and Concentrations
Mathematics
Project Advisor 1
Stefan Mendez-Diez
Abstract/Artist's Statement
In 2016 Donald Trump stunned the nation and not a single pollster predicted the outcome. For the last few decades, pollsters have relied on phone banking as their main source of information. There is reason to believe that this method does not present the complete picture it once did due to several factors--less landline usage, a younger and more active electorate, and the rise of social media. Social media specifically has grown in prominence and become a forum for political debate. This project quantitatively analyzes political twitter data and leverages machine learning techniques such as Naive-Bayes to model election results. Early results are promising, and a true evaluation of the model will come from testing in future elections.
Open Access Agreement
Open Access
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Vinnakota, Rao B., "Predicting How People Vote From How They Tweet" (2019). Senior Projects Spring 2019. 214.
https://digitalcommons.bard.edu/senproj_s2019/214
This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.
Included in
Analysis Commons, Artificial Intelligence and Robotics Commons, Databases and Information Systems Commons, Numerical Analysis and Computation Commons