Instagram Is Using Machine Learning to Block Offensive Comments The Facebook-owned social network on Thursday started rolling out two new machine learning-powered filters that will shield you from offensive and spammy comments.
This story originally appeared on PCMag
Instagram is intensifying its efforts to shield users from unpleasant content.
The Facebook-owned social network on Thursday started rolling out two new filters that will block offensive and spammy comments if you turn them on.
"Powered by machine learning, today's filters are our latest tools to keep Instagram a safe place," Instagram CEO and co-founder Kevin Systrom wrote in a blog post. "Our team has been training our systems for some time to recognize certain types of offensive and spammy comments so you never have to see them."
Just head over to your comment settings (click the settings menu from your profile and scroll down to tap "Comments") then toggle on "Hide Offensive Comments." After doing so, Instagram will automatically hide potentially unsettling comments on your posts. Instagram is launching this comment filter in English to start, but plans to expand it to more languages in the future.
"Many of you have told us that toxic comments discourage you from enjoying Instagram and expressing yourself freely," Systrom wrote.
When you have the filter turned on, benign comments will appear as they normally do, so you shouldn't miss anything you actually want to see. You can also still report any offensive comments that make their way through the filter, manually delete specific comments, or completely disable commenting for specific posts.
Instagram last fall introduced an option that lets you filter out comments based on a set of words you choose or a default list of terms that are often reported as inappropriate. This new offensive comments filter goes beyond that, an Instagram spokesman told PCMag -- it's automated and uses machine learning.
Meanwhile, Instagram's other new filter looks for "obvious spam" in comments, and wipes it from your posts and live videos. The filter will remove spam written in English, Spanish, Portuguese, Arabic, French, German, Russian, Japanese and Chinese.
"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. "Our work is far from finished and perfect, but I hope we're helping you feel safer and more welcome on Instagram."
These new features come after Instagram in March started blurring out photos and videos it deems "sensitive," so you don't have to see them in your feed or on someone's profile, unless you want to. That could include content shared by animal rights groups to expose animal testing conditions or animal abuse, or content that raises awareness of humanitarian crises around the world, such as famine and the impact of war, according to Instagram.
