SentimentAnalysis analyzes the sentiment (positivity or negativity) of a message. For instance, "I love you" is very positive, while "I hate you" is very negative. A statement like "I eat burgers" carries no significant connotation, so it is neutral.
The sentiment of a message is estimated as you type by using the Senticnet5 database. The sentiment is displayed on the bar at the bottom of the screen.
However, Senticnet5 is limited because it does not understand context, merely individual words and phrases. So, we used the Azure Sentiment API (called after each sentence to limit resource usage). This verifies and corrects the preliminary asessment of the Senticnet database, providing more accurate information.
/src: Contains flask app, entry point is index.js.
/static: Contains all static site content.
Main.py: the backend of the website, built on Flask
Analyze.py: Sentiment analysis functions
Senticnet5.py: The Senticnet database stored as a python dictionary