Inspiration
WHO declared the current COVID-19 related fake news an infodemic. With incorrect information flowing through our social media feeds, it gets tougher to differentiate what's real and fake.
What it does
Our solution interfaces chatbots distributed across major social media channels (Twitter, Whatsapp, Facebook) to run a check against a machine learning system to check if a post is real or fake.
How I built it
Our ML implements stance detection. Using a large set of default sources with hardcoded reputability, our database of sources continues to become more accurate with each web scraping by adding new sources and articles. To ensure this makes our algorithm better, the weights of each source are adjusted according to how much each new article agrees or disagrees with sources determined to be reputable. In the future, we would love to implement deep learning to further advance this ‘learning’ aspect of our reputability, but the current system more than supplies proof of concept
Challenges I ran into
Finding a new perfect classifier to correctly identify a fake COVID-19 news.
Accomplishments that I'm proud of
Research and benchmark on similar tools application in political news.
What I learned
How to wrongly classify fake news using fake or real datasets.
What's next for Hoaxy
Prototype implementation.
Log in or sign up for Devpost to join the conversation.