Term long project completed for EECS 510 (Social Media Mining) at Northwestern University, Spring 2017.
Project report can be found here
Given below is a flowchart outlining the steps taken towards completing this project.
tweepy_test.py - collects tweets using Twitter API by tracking certain keywords.
python-twitter_test.py - collects tweets using Twitter API of specific user
preprocessing.py - reads in the collected tweets, cleans and preprocesses it
wordprocessing.py - takes in a txt file, creates bag of words after doing stemming and returns the top 50 frequent words
smmgeo.py - extracting City and State name from place attribute