We may earn a commission if you click a deal and buy an item. If you're using an ad-blocker you might miss out on seeing the deals. Learn More

It’s machines vs trolls as Twitter unveils new plan to silence abusers

Twitter has finally (FI-NAL-LY) unveiled a way to silence the trolls – it’s using machine learning to hide the tormentors tweets from the feeds of the tormented.

The company will hide certain replies from conversations and search results in a bid to “improve the health of the conversation” on Twitter.

Those tweets will still be available, but users will have to manually click “show more replies” in order to reveal them.

So how is Twitter picking up on the trolls? Well it’s more than a case of monitoring the words used by trolls in abusive tweets.

Twitter is using machine learning to study whether email addresses are unconfirmed, or whether users are signing up for multiple accounts at the same time. It’ll also hide tweets from people who mention accounts multiple times, without that account following them back.

Related: Best smartphones

Twitter says its testing has shown positive results, with a 4% drop off in reported abuse from search and 8% fewer reports of abuse from within conversations.

Twitter acknowledges there’s a long way to go, but says its tech will learn more (and make mistakes) over time.

In the blog post, Twitter said: “This technology and our team will learn over time and will make mistakes. There will be false positives and things that we miss; our goal is to learn fast and make our processes and tools smarter.

“We’ll continue to be open and honest about the mistakes we make and the progress we are making. We’re encouraged by the results we’ve seen so far, but also recognize that this is just one step on a much longer journey to improve the overall health of our service and your experience on it.”

Do you trust Twitter to finally tackle to the trolls? Drop us a line @TrustedReviews on… erm… Twitter. And keep it friendly, yeah? 

Unlike other sites, we thoroughly review everything we recommend, using industry standard tests to evaluate products. We’ll always tell you what we find. We may get a commission if you buy via our price links. Tell us what you think – email the Editor