The tool is powered by machine learning, with Instagram saying in a blog post that it has been training its systems for "some time" to recognize certain types of comments, saying that the capabilities of the software will improve over time.
"Users will also be able to turn off this filter by clicking on the "..." settings menu from profile and scrolling to tap "Comments". They then fed most of this data into DeepText, which created algorithms based on what it found in the spam comments.
As for spam, which is rampant on the service, machine learning will be doing the heavy lifting.
"We believe that using machine learning to build tools to safeguard self-expression is an important step in fostering more inclusive, kinder communities", Systrom wrote.
DeepText is now in limited deployment on Facebook, but immediately after learning about the AI, Instagram's top people wanted to test it out on their own platform.
That filter will then block certain comments on posts and in live videos.
In addition, a new spam filter is getting a formal introduction today which is available in nine different languages. But still, Instagram wants to serve the best experience for their users. "Our work is far from finished and flawless, but I hope we're helping you feel safer and more welcome on Instagram".
In the seemingly never-ending fight against spam and generally low-quality comments on the internet, Instagram is taking new approaches in cleaning up comments on photos and videos.
- Instagram is flipping the switch on a system that will automatically detect mean, offensive and harassing comments and make sure that people never see them, TechCrunch reports. Since Instagram specifically mentions that the algorithms will "improve over time", expect them to be a little rough around the edges.
Both of these new filters are rolling out now.