Twitter Topic Modeling

This project uses the techniques for recommender systems in an unexpected way to help model topics found on Twitter. I extract topics from tweets using matrix factorization. This method assumes every tweet is a combination of several topics weighted by their prevalence in the text. This approach in fact finds a low-dimensional representation of the tweets (through the topic weights).
For this project, I worked with tweets about the pandemic from over a year ago when the pandemic recently entered our lives. The dataset is obtained from Kaggle and the preprocessing we have done followed the steps here - https://www.kaggle.com/satanizer/covid-19-tweets-analysis. For computational speed I will analyze a dataset from one day: April 30, 2020.