Instagram turns to machine learning to protect its users from toxic comments and spam

Instagram toxic comment filter

Instagram is introducing two new filters to help protect its users from comments that might contain hateful content and spam.

The first, a filter for blocking toxic comments, will, using a machine learning algorithm, automatically block “certain offensive” post and live video comments. Users can enable the feature by navigating to the “Comment Settings” section of the app’s main settings menu. Once there, a toggle titled “Hide Offensive Comments” turns on the feature.

According to Instagram, this new filter is currently only available in English, though the company says it will add support for additional languages a later date.

Additionally, Instagram is also adding an anti-spam filter. Like the toxic comment filter, the spam filter will use a machine learning algorithm to filter out spam comments 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. Our work is far from finished and perfect, but I hope we’re helping you feel safer and more welcome on Instagram,” said Instagram CEO and co-founder Kevin Systrom in the blog post announcing the changes.