Social Media

Twitter Deploys New Filter in DMs to Weed Out Abusive Content



Twitter is continuing with its long-running attempts to deal with abuse on its service. The latest effort is the trial of a filter that puts potentially abusive Direct Messages out of view.

Announcing the new feature in a tweet, the company said: “Unwanted messages aren’t fun. So we’re testing a filter in your DM requests to keep those out of sight, out of mind.”

The new section can be found by going to your Messages and tapping on the existing Message Requests button that contains content from people you don’t follow.

Below any new messages, you’ll see a note saying: “Show additional messages, including those that may contain offensive content.” Finally, tap on Show to view any messages that Twitter’s filters suggest may contain offensive content or spam.

Its usefulness will depend largely on the accuracy of Twitter’s algorithms to accurately single out unwanted messages. If you find it’s not working as advertised at the current time, it may be worth giving the team some time to hone the filter’s capabilities.

If it works well, the feature will be a welcome addition to the microblogging service for those who prefer to keep their Direct Messages inbox open to one and all.

Of course, if you’d rather not receive any messages from people you don’t follow, it’s easy to put a block in place. Simply tap on your Twitter profile, select Security And Privacy, and then Privacy And Safety, and then ensure the button for Receive Messages From Anyone is in the off position.

While Twitter still faces plenty of criticism for its efforts at purging abusive content from its site, it has steadily been introducing various measures in a bid to tackle the problem.

In a blog post in April, the San Francisco-based company said that while previously it only reviewed potentially abusive tweets if they were reported to its team by the user, it now makes it “a priority to take a proactive approach to abuse in addition to relying on people’s reports.”

It added: “Today, by using technology, 38% of abusive content that’s enforced is surfaced proactively for human review instead of relying on reports from people using Twitter. This encompasses a number of policies, such as abusive behavior, hateful conduct, encouraging self-harm, and threats, including those that may be violent.”

Twitter said it’s continuing to work on increasing the speed of its technology so that it can further improve its ability to deal with inappropriate content and take action before it’s reported.








READ SOURCE

This website uses cookies. By continuing to use this site, you accept our use of cookies.