Inspiration 💎

Our mission is to try to tone down online content to be more appropriate and inclusive for everyone.

What it does ⭐

By locating potentially offensive content on twitter using phrases gathered from hate speech, we can take down or fix tweets that may offend somebody. It also teaches you about terms you may not have known were offensive

How it Works 🔎

Users will search up twitter handles e.g. @Twitter. Based off of this we retrieve all the uses twitter post data, this includes every ones of their posts and even comments to the post. Comparing the tweet contents to a hate speech database we can determine exactly what might be considered an offensive term.

Challenges We ran into 💪

React 😍

Future improvements ✨

Looking ahead implementing a way to use context of tweet to improve accuracy of determining if a tweet is offensive and to scan images for inappropriate content.

Share this project:

Updates