Instagram uses AI to filter offensive comments and spam

Comment filtering service restricted to English language for now

Instagram has started using artificial intelligence to block offensive comments and spam.

According to a report, the Facebook-owned photo sharing service officially launched a comment filtering mechanism on Thursday.

“Many of you have told us that toxic comments discourage you from enjoying Instagram and expressing yourself freely,” said Instagram CEO and co-founder Kevin Systrom in a blog post. “To help, we’ve developed a filter that will block certain offensive comments on posts and in live video.”

Along with a new spam filter, which Instagram had been quietly testing over the last couple of months, the photo-sharing giant will filter abusive comments. The comment filtering service is restricted to the English language but spam is also detected in Spanish, Portuguese, Arabic, French, German, Russian, Japanese, or Chinese.



Comment filters are enabled by default but can be turned off.

Comment filtering is done through a machine learning algorithm that uses a test set of data with not just keywords but also contexts and relationships. For example, an f-word between friends may have a completely different context than a slur hurled at a stranger.



Instagram’s comment and spam filters are based on DeepText, an artificial intelligence effort developed in-house at Facebook.