xrosliang / fake-news-1

This Repository houses all of my efforts in trying to use new techniques to detect Fake News. I will be adding new models, techniques etc. regularly. I also provide documentation and explanation of the code!

Fake News

I have always had the dislike for things that were misleading, deceptive or purposefully crafted to trap you. I had a fear for all things 'fake'. This is what has motivated me to spend my time and hopefully research in-depth into fighting this major societal problem, Fake News. A report by Gartner reinforces this by quoting that "by 2022, most people in mature economies will consume more false information than true information". Can we imagine leaving in a world where the 'fake' outweighs the 'real'? We will be put into an alternate reality that has the potential to influence and control us.

Fake News 1

This uses the fake_or_real_news.csv file that was prepared by George McIntire in 2017 - see https://opendatascience.com/how-to-build-a-fake-news-classification-model/. The dataset has about 6,000 items, consisting of the headline and text of a news article and the label, FAKE or REAL.

I consistently got an accuracy of over 98% as compared to the original accuracy of 91.7% by George McIntire

Currently trying to host it as a website and provide a real service

Have more ideas? Contact me ASAP

Contact me here: [email protected]