Skip to content

emote-sentiment-analysis/backend

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Backend

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.

Frontend - React App

/src: Contains flask app, entry point is index.js.

/static: Contains all static site content.

Backend - Flask App

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

About

Analyzes sentiment of messages in realtime

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages