Machine learning technology allows us to track emotional experiences

Every decision we make is driven by emotion, but until now, measuring human emotion in real time has been impossible. However, according to new research from Rotterdam School of Management, Erasmus University (RSM) we can now successfully track, moment to moment how someone really feels.

Esther Eijlers, Dr Maarten Boksem and Professor Ale Smidts have developed a new method to measure and track emotions in the brain using electroencephalography (EEG).

They collected EEG data from 40 students while they watched short videos that were each designed to trigger a specific emotion: happiness, sadness, fear and disgust. Participants viewed five short clips for each of the four emotions. Using machine learning the researchers then classified the emotional content of these clips based on the frequency and topography of the EEG signal.

According to Esther Eijlers “The results showed that the algorithm we used can successfully predict which emotions were experienced during the viewing of the video clips.

“The ultimate validation that the classification algorithm worked came when we showed the participants a clip from the animated Pixar movie ‘Up’. The clip tells the story of the lives of a man and woman who get married, and grow old together.

“We estimated the average happy and sad responses across participants, second-by-second during the movie clip. It appeared that the emotional response, which was estimated based on the EEG data, was able to accurately track the main ups and downs of the story.”

Measuring emotional experiences has always been challenging. People are not often honest about how they really feel, and even if they are, it is often very difficult to put emotional experiences into words, particularly when these emotions are ongoing.

Being able to accurately measure emotional experiences with a high temporal resolution is extremely useful for businesses. It means they can understand the emotional effect their product, commercial, website or customer service has on consumers. When this method becomes commercially available in the future, it will be a valuable tool for tracking customer experience.

The research published in PLoS ONE.

ENDS
For more information, a copy of the paper to speak to, Esther Eijlers, contact Kate Mowbray at BlueSky PR on kate@bluesky-pr.com or call +44 (0)1582 7979 57