Twitter has acquired London-based Fabula AI to advance machine learning research and technologies both within the company and beyond, all to protect its users from fake news and misleading information across the internet.
Founders Damon Mannion, Ernesto Schmitt, Federico Monti and Michael Bronstein launched Fabula AI in 2018. Michael, the company’s chief scientist, devised and developed the innovative group of algorithms along with Monti and Davide Eynard, fellow researchers from the Università della Svizzera italiana Institute of Computational Science. The company’s patented Geometric Deep Learning technologies were brought to fruition along with Nanyang Technology University in Singapore, the Swiss École Polytechnique fédérale de Lausanne and Tel Aviv University in Israel.
“Instead of focusing on content, the new system analyses the processes that generate news items, in an automated fashion, identifying models useful to distinguish real news from fake,” Damon wrote in an announcement on the company’s blog.
Geometric Deep Learning can detect fake news online within milliseconds of processing 2 to 20 hours after its publication, Michael explained in a blog post. To put that figure into perspective, the average manual fact checker needs 8 hours to fully clear a fake news story.
“The performance of FABULA’s Geometric Deep Learning algorithm is unparalleled,” he proclaimed.
On June 3, Twitter released a statement to announce the company’s collaboration with the groundbreaking research startup.
“We are really excited to join the ML research team at Twitter, and work together to grow their team and capabilities,” Michael said. “Specifically, we are looking forward to applying our graph deep learning techniques to improving the health of the conversation across the service.”
Senior Director of Engineering at Twitter, Sandeep Pandey is in charge of the ever-developing research group at the social media giant, which plans to focus on emerging technologies such as graph deep learning, natural language processing, reinforcement learning, recommendation systems and machine learning ethics.
“This strategic investment in graph deep learning research, technology and talent will be a key driver as we work to help people feel safe on Twitter and help them see relevant information,” wrote Twitter CTO Parag Agrawal. “Specifically, by studying and understanding the Twitter graph, comprised of the millions of Tweets, Retweets and Likes shared on Twitter every day, we will be able to improve the health of the conversation, as well as products including the timeline, recommendations, the explore tab and the onboarding experience.”