FakeFews
Facebook Fake News Classifier! (Currently experiencing 95% testing accuracy using k-fold cross validation)
Summary
Candidate solution for Facebook's fake news problem using machine learning and crowd-sourcing. Takes form of a Chrome extension. Developed in under 24 hours at 2017 Crimson Code hackathon at Washington State University.
Some notes:
- Python secure server (with classifier and training data) lies in ./server
- Chrome extension lies in ./client
- Server, along with training data, is currently stored locally. Plans are to host these on external server soon.
- Chrome extension is not yet available on Chrome App Store - this is in the works!
Example
Here's an example classification of fake news, as would appear in your Facebook feed:
Contributions
This was a great and challenging project, and we plan on taking this further. Of course, this couldn't have been completed without the rest of team SlickBits:
- Shyam (@gopshyam)
- Anand (@Andyrocks143)
- Giridhar (@mgiridhar).
These guys have talent and persistence.
This work is under a Non-commercial Creative Commons license under the group SlickBits. If you use any part of this code, please add attribution to our team.
