Machine learning technology allows us to track emotional experiences
The new method was developed by a team from Rotterdam School of Management, Erasmus University
31 May 2019 | 0
Human emotions can now be tracked and measured, according to research from Erasmus University Rotterdam.
Developed by Ester Eijlers, Dr Maarten Boksem and Professor Ale Smidts, the innovative new method uses electroencephalography (EEG) to chart emotional response.
To collect EEG data, 40 students were shown videos with the hope of sparking specific emotions. The team tested for happiness, sadness, fear and disgust. Five clips were shown per emotion.
Using machine learning, researchers then classified the emotional content of the clips based on the EEG signal response.
Commenting on the results, Eijlers said “the algorithm we used can successfully predict which emotions were experienced during the viewing”.
The ultimate validation came from Pixar’s Up. “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”
For businesses, this tool will significantly boost understanding of how consumers respond to a product, service or commercial.
The research was published on PLoS ONE.