1. Make sure all the requirements are installed. (tweepy, flask, Tensorflow, Keras, Numpy)
2. Open terminal, type python app.py
3. Go to your browser, and type http://127.0.0.1:5000

app.py uses the saved weights, if you want to train your own model, download the Twitter Sentiment Analysis Training Corpus Dataset from http://thinknook.com/wp-content/uploads/2012/09/Sentiment-Analysis-Dataset.zip. Make sure that the csv is saved as ./s-a-d.csv (in the same directory as sent-a.py)

It took around an hour to train the model on a Google Cloud Compute VM with 6 cores and 25GB RAM.