Ever seen an office meltdown that had been brewing for some time?
Well, Brigham Young University professor Jeffrey Jenkins says he can tell one's anger level, as well as overall emotional state, by the way he or she moves a computer's mouse.
Using data points from a cursor's movement and speed, Jenkins and his team can detect how deviations in the movement can indicate one's emotions. Negative emotions can affect whether a user makes a purchase and remains a loyal customer, he notes. "We utilize attentional control theory to explain how mouse cursor movements can be a real-time indicator of negative emotion."
With this patented technology, which is licensed to a startup company, BYU's information systems expert says he can detect when people experience everything from anger to frustration, sadness and confusion, all by the way they move their mouse and the cursor's overall speeds.
"Using this technology, websites will no longer be dumb," Jenkins told Phys.org. "Websites can go beyond just presenting information, but they can sense you. They can understand not just what you're providing, but what you're feeling."
A common misconception that people have is when their coworkers are angry, they begin moving their mouse quicker and click more rapidly. Not true. It's actually the opposite.
"It's counterintuitive. People might think, 'When I'm frustrated, I start moving the mouse faster,' " Jenkins said. "Well, no, you actually start moving slower."
Jenkins believes his practice could be put into place by web developers to measure how specific websites might bring out negative emotions amongst users and visitors, alike. And that goes for mobile users surfing the web as well, as the same technology could be put to use with swipes.
"Traditionally it has been very difficult to pinpoint when a user becomes frustrated, leading them to not come back to a site," Jenkins said. "Being able to sense a negative emotional response, we can adjust the website experience to eliminate stress or to offer help."
The research team's continuing work is described in an abstract and will be included in an upcoming edition of MIS Quarterly, a peer-reviewed journal published by the Management Information Systems Research Center at the University of Minnesota.
