A project to scrape twitter for tweets about covid19 vaccinations IOT learn data processing Project is to be written in python using the twitter API and libraries including tweepy and searchtweet. Main outcomes are evaluatition of different methods of Topic Modelling (Unsupervised learning to determine what other topics are brought up when discussing vaccination), and the data preprocessing used. Word cloud tracking 100 most popular words for each discovered topic Data is to be correctly preprocessed, involving stemming and removing stop words. Evaluation of different techniques of feature extraction and modelling.
Useful files are the json files, the file in the kmeans folder, gensim-lda-clean, and maybe the preprocessing file