Break-the-Buzz

Inspiration:

Rumour is the fastest traveller. Scam spams, fake news & bogus tales pose a threat to many. It serves as a kick at the can to the crackers out there. Clickbait spreads faster through media. Humans are more likely to spread lies faster than facts.

What it does:

With the advancement of developed neural technologies, it is pretty possible to break the buzz as it acts as a discriminator to detect discrepancies in sources and articles so as to maintain legitimacy. Its main purpose is to distinguish real and fake information.

How we built it

It can be implemented through Artificial Intelligence systems which would enhance the detection programs to scrutinize the authenticity of articles and information. A Bidirectional Neural Network and LSTM based deep learning model to detect fake news from a given news corpus. Some of these datasets include: *RealNews: This dataset was used to train Grover and has over 5,000 authentic publications that require 120 GB of space. *Kaggle: This dataset takes up around 57 MB of disk space and contains 13,000 rows and 20 columns of data. *George McIntire: Named after the data visualization analyst, this set of fake news data requires 31 MB of disk space.

Challenges we ran into

*Adversarial machine learning which is the process of creating malicious or misinforming content that can slip past detection programs. *Deepfakes which are artificially generated videos and photos that can superimpose the physique and face of one person on another to make it seem like they carried out a certain action. *If the content isn’t convincing enough, the generators used keep reproducing text until and unless it turns out to be real.