{"id":349494,"date":"2021-10-07T10:31:19","date_gmt":"2021-10-07T07:31:19","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/twitters-heated-discussion-prompt-sounds-complex-to-execute\/"},"modified":"2021-10-07T10:31:19","modified_gmt":"2021-10-07T07:31:19","slug":"twitters-heated-discussion-prompt-sounds-complex-to-execute","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/twitters-heated-discussion-prompt-sounds-complex-to-execute\/","title":{"rendered":"#Twitter\u2019s \u2018heated discussion\u2019 prompt sounds complex to execute"},"content":{"rendered":"

“#Twitter<\/a>\u2019s \u2018heated discussion\u2019 prompt sounds complex to execute<\/strong>”
\n<\/p>\n

Twitter has been experimentinga lot with features related to conversations on the platform over the last few months. Its latest test involves a warning for when you\u2019re about to enter a \u2018heated discussion.\u2019<\/p>\n

The social network said that it\u2019ll display a prompt on Android and iOS for conversations it thinks can get intense. The prompt seems to remind you of basic moral values like \u201cRemember the human (in the conversation) and \u201cdiverse perspective have values.\u201d<\/p>\n

\n

Ever want to know the vibe of a conversation before you join in? We\u2019re testing prompts on Android and iOS that give you a heads up if the convo you\u2019re about to enter could get heated or intense.<\/p>\n

This is a work in progress as we learn how to better support healthy conversation. pic.twitter.com\/x6Nsn3HPu1<\/a><\/p>\n

\u2014 Twitter Support (@TwitterSupport) October 6, 2021<\/a><\/p>\n<\/blockquote>\n

The prompt doesn\u2019t come as a surprise to me. I\u2019ve seen people fight on topics ranging from environmental awareness to the best flavor of a snack. ANY discussion can get heated on this bird site. But I\u2019m not completely convinced that reminding trolls about human values will stop them from slinging someone\u2019s name in the mud.<\/span><\/p>\n

Effectiveness aside though, there are also plenty of technical difficulties in detecting these discussions<\/span>. If an AI is at work, it will need to understand the correlation between words and cultural connotations of sentences used in a particular conversation.<\/p>\n

In the past, trolls have fooled algorithms to believe a conversation is non-toxic by changing some words, inserting positive words in sentences, or using different spellings of a swear.<\/p>\n

Also, at the moment, this feature seems to be limited to English. In a country like India, where a large set of the population is multilingual, someone can easily slip in a few words from another language and trick the algorithm into thinking a conversation is going well.<\/p>\n

We\u2019ve asked Twitter to share more details on how the algorithm works, and we\u2019ll update the story if we hear back.<\/p>\n

Twitter started using machine learning to reduce toxicity on the platform last year. Its newest experiment of intense conversation prompts is perhaps one of the more ambitious endeavors in that category that\u2019ll test its AI might on multiple levels.<\/p>\n

Did you know we have a news<\/a>letter all about consumer tech? It\u2019s called Plugged In \u2013 and you can subscribe to it right here.<\/i><\/p>\n<\/div>\n