MIT Software to Read the Emotion of the Masses

What’s the Latest Development?

After MIT researchers fine-tune software that can read human facial expressions for emotion, the next step will be to apply the technology to crowds of millions of people to get a feeling for a population’s general mood. “The software tracks 22 points around the mouth, eyes and nose, and notes the texture, colour, shape and movement of facial features. The researchers used machine-learning techniques to train the software to tell the difference between happiness and sadness, boredom and interest, disgust and contempt.” A commercial version of the software is now being used to test people’s reaction to advertisements. 

What’s the Big Idea?

Rana el Kaliouby, a researcher at MIT’s Media Lab Affective Computing group, says commercial applications of facial recognition technology are merely the “low-hanging fruit”. “The software is getting so good and so easy to use that it could collate millions of peoples’ reactions to an event as they sit watching it at home, potentially replacing opinion polls, influencing elections and perhaps fuelling revolutions.” Originally from Egypt, el Kaliouby was present during the uprisings against former-president Hosni Mubarak. She hopes that leaders might be convinced of their own unpopularity if the feelings of entire populations can be gathered more easily. 

Photo credit: Shutterstock.com