Fake News Detector

Inspiration

Sick of falling for fake news and being deceived, we developed an AI model which uses Natural Language Processing to get rid of this problem.

What it does

This model detects whether a URL contains fake or real news (scam or not).

How we built it

We used NLP (Natural Language Processing) and Google Colaboratory to build this model. We identified the confusion matrix, where our model was getting a low accuracy, and developed a featurizer which makes the prediction rate have a higher accuracy.

Challenges we ran into

Some challenges we ran into were that we couldn't come up with any ideas for the model to have a higher accuracy.

Accomplishments that we're proud of

One big accomplishment was when we presented this in the prestigious program "InspiritAI" we won the best presentation/model award.

What we learned

We learned how to use ML strategies such as NLP and Logistic Regression to build such a strong and useful model.

What's next for Fake News Detector

We hope to be able to come up with more ideas to make the accuracy even higher. Right now it is at a 97% accuracy.

Built With

• google-colab
• natural-language-processing
• python