Twitter launches updated offensive comment alerts on iOS and Android

Twitter launches updated offensive comment alerts on iOS and Android


After recently revive his test warnings on replies to tweets containing potentially offensive remarks, Twitter is now deploy new updated version of prompts, on iOS and Android, which use an improved detection algorithm to avoid misidentification, while also aiming to provide more context and options to help users better understand what warning alerts mean.

The new version of the prompt aims to be more useful and polite, while improving the determination of the meaning of tweets.

As explained by Twitter

:

“In early testing, people were sometimes unnecessarily enticed because the algorithms that fed the prompts struggled to capture nuance in many conversations and often didn’t differentiate between potentially offensive language, sarcasm and friendly jokes. . Throughout the experimentation process, we analyzed the results, collected public comments and strove to correct our errors, including detection inconsistencies. “

This led to a significant increase in performance throughout the initial test pool, which has now given Twitter the confidence to expand the option,

The updated offensive response algorithm will now take into account items such as the nature of the relationship between the author and the replicator (e.g. how often they interact) and will include better detection of strong language, including profanity, while the prompts themselves will now offer more options for allow users to glean more context and provide comments to Twitter about the alert.

Twitter Offensive Comment Alerts

Twitter reports that, more specifically, 34% of users in initial testing for the new prompts ended up revising their initial response, or decided not to send their response at all, while users also, on average, posted 11% fewer offensive responses in the future. after receiving the alert.

This focuses on a key part of the larger online engagement space, with Facebook research showing that a basic misinterpretation plays a key role in worsening anxiety, with users often misunderstanding the responses in return, causing unintentional conflict.

Adding an element of friction here, simply asking users to re-evaluate their response, may be enough, in many cases, to avoid further negative impacts, improving the overall discourse on the platform.

Which Twitter has been doing a lot better lately. Long known for its toxicity, Twitter has made conversational health a much more important focus, which has made the platform, more generally, a more open and welcoming space.

There are, of course, still significant concerns on that front, and it’s a battle that will likely never be “ won, ” as such, but little prompts and tweaks like this play a role. in improving the Twitter experience for many.

The expansion and update here will add to that further.





Source link

Leave a Reply