There are several ways to tell if someone is angry: the words they use, the tone of their voice, their facial expressions, or even the way someone moves a computer mouse.
Yes, you read that last one correctly. In an effort to gauge computer users’ emotions from the other end of the interwebs, scientists have developed a way to tell whether you are angry just by analyzing the way you click and move your mouse.
Jeffrey Jenkins, an information systems professor at Brigham Young University, says people who are experiencing anger — and other negative emotions like frustration, confusion or sadness — become “less precise in their mouse movements and move the cursor at different speeds.” Jenkins detailed his research in a paper published by the University of Arizona.
With a little help from modern technological advances, Jenkins can gather and process enough data points from a person’s cursor movements to measure deviations that indicate their emotional state.
“Using this technology, websites will no longer be dumb,” he said. “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.”
His research suggests that when users are upset or confused, their mouse handling becomes erratic and no longer follows a straight or gently curving path, instead becoming more jagged and sudden. The movements then become slower.
“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.”
This research will be most beneficial to web developers who can use the tool on their websites to adapt or fix sore points that bring out visitors’ negative emotions.
“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 technology Jenkins developed has been patented and he is now in the process of refining it via a local startup that holds the license. He added that, with further developments in the future, the same concept can also be applied to mobile devices.