In a bid to detect network manipulation in time, micro-blogging site Twitter has acquired London-based start-up Fabula AI.
"We are excited to announce that we have acquired Fabula AI, a London-based start-up, with a world-class team of Machine Learning (ML) researchers who employ graph deep learning to detect network manipulation," Parag Agrawal, Chief Technology Officer (CTO), Twitter, wrote in a blog post on Monday.
Parag says that Machine learning plays a key role in powering Twitter from onboarding people on the platform to connecting them with relevant conversations, Twitter leverages machine learning (ML) across a multitude of our product surface areas.
The acquisition announcement came after Twitter claimed it took down over 2,800 fake accounts linked to Iran in May.
“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. 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,” Parag wrote in the blog.
Fabula was founded by Michael Bronstein, Damon Mannion, Federico Monti, and Ernesto Schmitt. It is led today by co-founder and chief scientist Michael Bronstein and chief technologist Federico Monti, who began their collaboration together while at the University of Lugano, Switzerland. Bronstein is one of the world’s leading researchers in graph deep learning, and has pioneered its application in the realm of Internet companies.
In a blog post, the London-based start-up said its Geometric Deep Learning technology has high success rates of spotting fake news.
The Fabula AI team would join the Twitter team to stop spam and abuse and other strategic priorities in the future.
"We work to help people feel safe on Twitter and help them see relevant information. Specifically, by studying and understanding the Twitter graph, comprised of millions of tweets, re-tweets 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 said in the blog post.