Inspiration
Fake news is very divisive so its good to be able to identify it.
What it does
Identifies fake news based on semantics analysis. We generate the parts of speech list for an article and calculate the probability that such a transition came from a fake or real news source
How we built it
python
Challenges we ran into
Trying to combine two different classification models without leaking information was challenging but fun
Accomplishments that we're proud of
It works! The model accuracy also succeeds our expectations which is nice
What we learned
machine learning techniques
What's next for News Organiser based On Semantics Evaluation (NOOSE)
Get a larger dataset. Extend it to a browser or bot.
Log in or sign up for Devpost to join the conversation.