AI Is Working To Make Moviegoers More Emotional

AI Is Working To Make Moviegoers More Emotional

An AI algorithm can predict which parts of a film will generate the greatest emotional responses in audiences

Anna Johansson
  • 2 january 2018

Artificial intelligence can influence your travel plans, anticipate your online orders and improve efficiency around the house. In the entertainment sphere, there’s an AI technology to make you feel more while watching a movie. Researchers at the MIT Media Lab were able to train a machine to manipulate the emotional responses of video viewers. Their findings were published in collaboration with strategic consulting firm McKinsey & Company.

The MIT team examined the neural perceptions of thousands of people who watched movies, videos, online features and television programs in sections. They paired their reactions to a neural network, which guessed which parts of each clip would spark the greatest emotional response in humans. Over time, the neural network learned which parts created which human emotions more accurately, and now it can be used to help filmmakers generate the desired emotional response in their productions.

Now, if you think this means that movies will now be written by robots instead of humans, think again. The researchers examined a short film called Sunspring, which was written entirely by artificial intelligence, and found it to be awkward and nonsensical. That being said, the team thinks the technology could help filmmakers “by providing insights that increase a story’s emotional pull—for instance, identifying a musical score or visual image that helps engender feelings of hope.”

“As storytellers increasingly realize the value of AI, and as these tools become more readily available, we could see a major change in the way video stories are created,” they wrote. “In the same way directors can now integrate motion capture in their work, writers and storyboarders might work alongside machines, using their capabilities to sharpen their stories and amplify their emotional pull.”

It might seem like using the algorithm will result in the mass production of stories with identical story arcs and the end of originality. But some would argue that this is already happening, and that’s why the algorithm would be so useful. The researchers point out that it could be a great editing tool for those seeking to make their film a hit.

“These insights will not necessarily send screenwriters back to the drawing board, but they could inspire video storytellers to look at their content objectively and make edits to increase engagement,” they wrote.

AI has been used in the movies before to create greater emotional responses. Disney, for example, has used facial recognition to identify the ways audiences react to their films during test screenings, rather than relying on traditional survey results alone.

MIT Media Lab

+artificial intelligence
+future of storytelling
+MIT Media Lab

More in Entertainment


These IKEA Speakers Are Made For Spur-Of-The-Moment Parties

IKEA tapped Teenage Engineering to create a collection of products for the perfect home party, including speakers and LED lights

23 February 2018

Google Has Begun Replacing Apps With Neural Networks

Google is advancing its AI capabilities to give 'ambient awareness' to the Pixel 2 phone

23 February 2018

The Latest


A conference celebrating innovation in brand experience, retail experience and consumer culture.

May 18, 2018 | New York City

At PSFK 2017, Peloton Co-Founder and COO Tom Cortese discussed how the company aims to utilize the power of Web 2.0 to marry the comfort of home fitness to the high-energy engagement of celebrity-run classes.

September 27, 2017
No search results found.