A Flu Predictor App
A Real-Time software to measure how healthy your place of living is by analyzing tweets contents.
Aras Balali Moghaddam, Kazem Jahanbakhsh, Li Yu
Firefox OS App day (http://firefox-os-vancouver.eventbrite.com/).
This project has been implemented in order to measure the probability that you can catch the flu by taking into account the geographical distribution of sick people in your close proximity. It basically collects tweets posted on Twitter website and uses ML & NLP in order to compute the chance that a tweet is posted by a person who really has the flu.
The backend layer is written in Python and uses NLTK package. The front layer uses HTML5, JS, and CSS for visualization purposes. You can check running version of the web app from the following link:
http://www.kazemjahanbakhsh.com/codes/flu-predictor.html
**Please drop us a note at "k DOT jahanbakhsh AT gmail DOT com" if you have any questions.