Twitter isn’t really known for being a peace-loving place for like-minded individuals. It’s more of the opposite, where vitriol peaks and people won’t think twice to type a rage-fueled reaction to an erring politician, a “cancelled” celebrity, or just about anything that doesn’t align with their worldview.
Anger is always a valid feeling but sometimes it isn’t the best behavior to display, that’s why Twitter has rolled out a feature that lets you review an offensive, potentially regrettable reply.
With the new feature, Twitter’s algorithms will be able to detect if you’ve typed something “harmful or offensive” and will send you a prompt that offers the option to edit, delete, or send the tweet anyway.
It took Twitter a year to get the formula for the new feature right, spending much time to improve how the algorithm can consider the context of the conversation before sending out a prompt. This comes after criticisms raised that it “struggled to capture the nuance in many conversations and often didn’t differentiate between potentially offensive language, sarcasm, and friendly banter”.
“If two accounts follow and reply to each other often, there’s a higher likelihood that they have a better understanding of preferred tone of communication,” Twitter said in a blog post.
Since then, Twitter reports that the feature, which is set to come to Apple devices first then Androids later, has significantly reduced the volume of abusive language on the application.
“These tests ultimately resulted in people sending less potentially offensive replies across the service, and improved behavior on Twitter,” the micro-blogging platform described. “We learned that, if prompted, 34% of people revised their initial reply or decided to not send their reply at all. After being prompted once, people composed, on average, 11% fewer offensive replies in the future; if prompted, people were less likely to receive offensive and harmful replies back.”
Moving forward, Twitter says it will continue to explore how prompts and other forms of intervention “can encourage healthier conversations” on the social media platform and how it can be expanded to other languages.
That being said, we can only hope they’re cut out for the job of filtering Filipino profanities.