Press "Enter" to skip to content

Facebook Developed New AI-Based Tool to Identify Offensive Memes

Social networking major Facebook is developing new Artificial Intelligence (AI)-based to detect unpleasant content

Facebook described a system in its blog post called Rosetta that uses machine learning to identify text in images and videos and then transcribe it into something that’s machine readable. In particular, Facebook is finding this tool helpful for transcribing the text on memes. Facebook’s moderators cannot monitor every content manually that is posted on the enormous platform, therefore AI platform is being developed to assist them. Facebook says 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 company’s well-known moderation issues, a well-functioning system that can automatically flag potentially problematic images could be a real help.

Although text transcription tools are not new, Facebook is facing different challenges due to size of its platform and the variety of the images posted daily. Rosetta is said to be live now, extracting text from 1 billion images and video frames per day across both Facebook and Instagram. However, currently it’s unclear how Facebook is controlling this data. It’s useful for basic features such as photo search and screen readers, the blog post points out. Facebook is starting to put it toward much bigger goals such as figuring out what would be interesting to put in your News Feed, and, more importantly, figuring out which memes are just goofy memes, which are actually spreading hate speech or other offensive comments.