Instagram brings a new feature which automatically blocks offensive comments


Though the filters are rolling out today, you should expect a few hiccups as Instagram's machine learning tools improve.

The first automatically keeps certain offensive comments off your posts before you see them.

But while the offensive comment filter will initially only be available in English, the spam filter will also work in eight additional languages: Spanish, Portuguese, Arabic, French, German, Russian, Japanese and Chinese.

Instagram is also announcing an AI spam-filtering system today, too.

Facebook has ramped up efforts to curtail hate speech using machine learning and creating counterterrorism partnerships for education and advocacy.

Mr Systrom added: 'We'll launch this comment filter in English first, but will offer it in more languages over time'.

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.

Instagram is cracking down on unwanted comments.

"We believe that using machine learning to build tools to safeguard self-expression is an important step in fostering more inclusive, kinder communities", the post said.

- 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.

The spam filter looks for any obvious spam in comments, blocking it from your posts and live videos.

Instagram reportedly launched the DeepText system quietly back in October to take on widespread spamming. Users can activate this feature by triggering it in the comments section of the settings. If a comment is deemed inappropriate, members of the team will place the comment under categories like "bullying, racism and sexual harassment". Since Instagram specifically mentions that the algorithms will "improve over time", expect them to be a little rough around the edges.