Twitter tweaks algorithms to give trolls less prominence

Twitter tweaks algorithms to give trolls less prominence

Although Twitter employees have been caught on camera admitting that shadowbanning takes place on the platform, the company continues to publicly deny that it engages in the practice - they have even made such denials in Senate hearings.

The US social network, which has spent years coming under fire for failing to delete abusive messages, will not display tweets from users who have exhibited certain "troll-like" characteristics. For example it will look at how many accounts are registered to that particular user, if they constantly tweet and mention accounts that don't follow them, or if they might have been blocked by some users, and so on.

Twitter says that while many posts do not break its rules, many are still be in poor taste or offensive to a large number of users. But now, Twitter will also look at a greater variety of data points, including new behavioral analysis, including how many users block an account following a specific tweet or response to another tweet.

Twitter specified that users will still be able to view content that doesn't technically violate Twitter's policies by clicking on the "Show more replies" button.

By not taking into account the content of tweets, Twitter can roll out these changes worldwide because language will not be a factor.

To put this in context, less than 1% of accounts make up the majority of accounts reported for abuse, but a lot of what's reported does not violate our rules. Twitter's approach, which it outlined to reporters in a briefing on Monday, is distinct because it is content neutral and will not require more human moderators.

Google employees quit in protest against cooperation with the Pentagon
Project Maven aims to develop AI that can spot humans and objects in vast amounts of video captured by military drones . It means that a drone would be able to pick out a known terrorist in a crowd and centre any attack on that area.

USA -based microblogging giant Twitter has announced to implement "behaviour-based signals" to organize and present tweets to users.

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 is announcing a global change to its ranking algorithm this week, its first step toward improving the "health" of online conversations since it launched a renewed effort to address rampant trolling, harassment and abuse in March.

Dorsey and Harvey appeared optimistic that this new approach will have a significant impact on users' experience.

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 are making progress as we go", Dorsey said.

Related Articles