The AI will go along way in tracking images and texts on the platform – which even the company’s moderators can’t possibly look through on their own.
Facebook elaborated on ‘Rosetta’ on a blog post today. It’s a system that uses machine learning to identify text in images and videos and then transcribe it into something that’s machine readable. This tool makes it easy to identify memes – which are often as much a topic of scrutiny and controversy, as they are popular in general use.
Text transcription tools are nothing new, but Facebook faces different challenges because of the size of its platform and the variety of the images it sees. Rosetta is said to be live now, extracting text from 1 billion images and video frames per day across both Facebook and Instagram.
It isn’t immediately clear what Facebook is doing with the data. While it’s useful for features like photo search and screen readers, as the post points out – it also seems like Facebook will use it for bigger goals like putting interesting stuff in users’ news feeds, and more importantly—differentiating between goofy and offensive memes and comments.
Facebook states that text extraction and machine learning are being put to use to “automatically identify content that violates our hate-speech policy” and that it’s doing so in multiple languages.
Given the software giant’s infamous and publicly scrutinised moderation issues, a well-functioning system that can automatically flag potentially problematic images can be a real boon.