Instagram announced on its official blog Tuesday that it will be using machine learning to combat bullying on the platform.
According to a spokesperson, the new tech will be able to detect bullying in photos and captions.
WATCH: Instagram co-founders leaving Facebook
“While the majority of photos shared on Instagram are positive and bring people joy, occasionally a photo is shared that is unkind or unwelcome. 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,” Adam Mosseri, head of Instagram, said in the post.
However, Global News reached out for further clarification about exactly how a machine learning algorithm would detect bullying “in” photos.
A spokesperson from Instagram provided an example.”An example of a bullying tactic that the photo technology detects is comparing, ranking, and rating images and captions, such as split-screen images where a person is compared to another person in a negative way,” said spokesperson David Troya-Alvarez.
WATCH: This is how much you actually use Instagram
He went on to say that automation has already been used on the platform to stop spam attacks, pornography and terrorist content.
“We will continue to look at carefully at other ways to use automation,” Troya-Alvarez added.
The machine learning mechanism will be looking for signs of harassment in photos, such as attacks on a person’s appearance or character, or threats to their well-being.
When a photo is identified as likely containing “bullying content”, it will be sent to the Community Operations team for a “human-review.” At that point, if the photo is determined by the reviewer to violate Community Guidelines, it will be removed.
It’s important to note that Instagram has had a rocky few weeks. Mosseri was named head of the Facebook-subsidiary company last week, following the exit of co-founders Kevin Systrom and
Michael Krieger.
This move seems to follow the company’s announcement earlier this year that it would filter out bullying comments on its site through a feature that detects and blocks these comments altogether.
The feature has already started rolling out and will continue rolling out over the next few weeks.