Twitter has acquired Fabula AI, a London-based start-up who have created technology that uses deep learning to “detect network manipulation”, something that will come in handy for the social media site riddled with fake users and posts. Fabula uses graph deep machine learning to analyze numerous extensive datasets at once and extract information that average ML technology would not be able to identify.
“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,” said Parag Agrawal, CTO, Twitter.
“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,” Agrawal added.
Fabula is currently led by co-founder and chief scientist Michael Bronstein and chief technologist Federico Monti, after being created in Switzerland during thier univeristy years. Bronstein is “one of the world’s leading researchers in graph deep learning, and has pioneered its application in the realm of Internet companies.”
“We are really excited to join the ML research team at Twitter, and work together to grow their team and capabilities. Specifically, we are looking forward to applying our graph deep learning techniques to improving the health of the conversation across the service,” said Bronstein.
Once the acquisition is completed, Twitter said it will prioritize the “health of the conversation” that takes place on the app, and will begin developing technology that not only detects spam and abusive content, but will prevent it from spreading.
Bronstein also serves as the chair in Machine Learning & Pattern Recognition at Imperial College, which he will continue to hold while leading Fabula’s acquisition by Twitter.