Instagram to Begin Auto-Blocking Offensive Comments and Spam

"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.

Last December, Instagram added a feature that let users turn off comments on individual Instagram posts.

The filter will work both in posts and live video, and will block comments it finds abusive or offensive. After doing so, Instagram will automatically hide potentially unsettling comments on your posts. The filter is debuting in English only at first, but all raters employed in the project are at least bilingual, and Instagram is also expanding its spam filter to other languages, which means it's likely they'll deploy this tool for more regions over time, too. This setting is turned on by default.

Instagram said that the filter scanning for spam is created to work in Arabic, Chinese, English, French, German, Japanese, Portuguese, Russian and Spanish.

The comments are hidden from everyone except the person who made the offensive comment.

Instagram (NASDAQ:FB) launches an AI-backed offensive comment blocker and a multilingual spam filter, according to a company post.

Image caption Instagram say their process is currently 99% accurate and they are hoping this number will improve
Image caption Instagram say their process is currently 99% accurate and they are hoping this number will improve

Written remarks will otherwise appear as usual at Instagram, and users can opt to turn off the new filters.

The new AI-powered filter is available first in English, with additional language support arriving "over time". Instagram has also launched a new spam filter in nine languages. Instagram's engineers then came up with algorithms so that DeepText can do its magic on the app.

While it's unclear exactly how well DeepText worked in this trial run, Wired reports that Instagram CEO Kevin Systrom was "delighted".

"Facebook and Instagram are different platforms with different user experiences - from the follow model to how comments are used". If a comment is deemed inappropriate, members of the team will place the comment under categories like "bullying, racism and sexual harassment".

"The tools will improve over time".

  • Joey Payne