Twitter has acquired Fabula AI, a London-based startup that uses machine learning (ML) to help detect the spread of misinformation online.
Terms of the deal were not disclosed, but the acquisition will underpin a new research group at Twitter led by Sandeep Pandey, which will work toward finding new ways to leverage machine learning across natural language processing (NLP), recommendations systems, reinforcement learning, and graph deep learning, while it said that it will also focus on ML ethics.
Fabula was founded in 2018, and has developed a patented AI system it calls “geometric deep learning,” which are effectively algorithms that learn from large and complex datasets gleaned from social networks.
“Fake news” has emerged as an umbrella buzzword designed to describe the deliberate spread of misinformation, but Fabula AI at its core is really about helping to identify the authenticity of any information that circulates on social media — whether it’s deliberate or otherwise. Studies have shown that false and real news spread differently online, with the former spreading faster than the latter. And this is what Fabula focuses on: it detects the difference in how content is spreading on social media and allocates an authenticity score.
“As this technology detects the spread pattern, it is language and locale independent; in fact, it can be used even when the content is encrypted,” the company says on its homepage. “We also believe that such an approach, given it is based on the propagation pattern through huge social networks, is far more resilient to adversarial attacks.”
As with most of the major social media platforms, Twitter has faced its fair share of criticism over how it’s used to spread misinformation. And this latest move is designed to help “improve the health of the conversation” on Twitter, according to CTO Parag Agrawal.