The 'DeepMoji' AI that has used emoji to learn to detect sarcasm more effectively than HUMANS to help tackle online abuse

Mail Online | 8/7/2017 | Harry Pettit For Mailonline
Firefang (Posted by) Level 4
Click For Photo: http://i.dailymail.co.uk/i/pix/2017/08/07/18/430DC76800000578-0-image-a-28_1502126675266.jpg




An artificially intelligent robot that can understand sarcasm in social media posts better than humans has been developed by scientists.

The algorithm can decipher the tone of tweets, and researchers say it could be used to tackle online abuse.

Emoji - Post - Text - Robot - Subtext

By interpreting emoji used alongside a post's text, the robot can understand emotional subtext and identify if sarcasm is being used.

As well as detecting online abuse, it could be used to assess how people feel about brands, or to improve human interaction with AI programs such as chatbots.

Researchers - Massachusetts - Institute - Technology - AI

Researchers at the Massachusetts Institute of Technology created the AI, known as DeepMoji, by feeding it 1.2 billion tweets.

The robot analysed each tweet to understand how 64 popular emoji were used to express meaning.

Intonation - Voice - Body - Language - Way

'Because we can't use intonation in our voice or body language to contextualise what we are saying, emoji are the way we do it online,' Dr Iyad Rahwan, associate professor at the MIT Media lab in Cambridge, Massachusetts, told MIT technology review.

'The neural network learned the connection between a certain kind of language and an emoji.'

Researchers - DeepMoji - Emojis - Context

Researchers first taught DeepMoji how to use emojis in the appropriate context based on...
(Excerpt) Read more at: Mail Online
24 other people are viewing this story
Wake Up To Breaking News!
Satan's greatest desire is to convince the world he doesn't exist, and he has quite nearly succeeded.
Sign In or Register to comment.