Instagram is revving up the fight against bullying. During an announcement on how Instagram plans to help limit bullying in the run up to both the October’s National Bullying Prevention Month in the US and just before Anti-Bullying Week in the UK, the social networking giant revealed they are going to launch a new automated way of identifying incidents of bullying among user’s images.

Very little information was originally been made public by Instagram, aside from an announcement by the company’s new head Adam Mosseri when launching the new series of products aimed at reducing the level of harassment or bullying on the social network. “We are now using machine learning technology to proactively detect bullying in photos and their captions and send them to our Community Operations team to review,” said Mosseri.

But when reporters at tech site The Verge asked an Instagram spokesman for more information, the social networking giant divulged some more information: ”Speaking to The Verge, a spokesperson gave the example of the AI looking for split-screen images as an example of potential bullying, as one person might be negatively compared to another. What other factors the AI will look for though isn’t clear.”

It’s the first announcement for the new head Mosseri, who took up the position last week and comes off the back of a bullying comment filter launched in March. Last year Instagram topped a study by international anti-bullying charity Ditch the Label as the social network “most used for mean comments” after seven percent of young people said they had experienced bullying on the platform.