TwitterAnalysis

In this project, we take a deep dive into Trump and Biden’s Twitter followers. By utilizing data visualization techniques, entropic analysis, and machine learning modeling, we investigate the polarization between Trump and Biden followers, predict who a Twitter user is most likely to follow based on the accounts they follow, and analyze other significant trends.

Check out our website!: https://johnsont4.medium.com/twitter-analysis-trump-vs-biden-8dafa77ac7d5

To run this project for yourself:

1. Install all libraries (tqdm, os, twint, pandas, numpy, sklearn)
2. Run scrapeUsers.py to scrape followers from Trump and Biden (or whoever else you insert into the program)
3. Run dataCollector.py to create the 3 groups: Trump followers, Biden followers, and both followers
4. Run matrixCreator.py to create the matrices and target arrays
5. Use jupyter notebooks to import the matrices and target arrays and analyze the data however you want! (Our analysis can be found in FinalSubmission.ipynb)
6. *BONUS: Run youTry.py to see how likely a specific user is to follow Trump or Biden!

Thank you!

If you have any questions or concerns, please reach out! johnsont4@carleton.edu