One of the problems with workplace stress is the fact that it can sneak up on you, so by the time you realize you're stressed, you're already overdue for a break. Soon, however, it may be possible to warn of problematic stress by analyzing workers' typing and mousing.
In an ETH Zurich study led by research associate Mara Nägelin, a team of scientists monitored 90 test subjects as they performed typical office computer tasks – such as recording data or planning appointments – in a lab setting. Each participant's heart rate was monitored as they performed these activities, as was their mousing and keyboarding behaviour.
Additionally, while a control group was left to work undisturbed, other test subjects had to simultaneously take part in a job interview, or repeatedly respond to text messages. All of the participants were periodically asked how they were feeling.
It was found that the people who reported feeling most stressed tended to move their mouse more often, less precisely, over longer onscreen distances. By contrast, those who were less stressed made shorter, more direct yet also slower mouse movements.
Additionally, the stressed volunteers typed in "fits and starts" and made more mistakes, while the relaxed test subjects took fewer but longer pauses, with fewer mistakes. This outcome fell in line with what is known as the neuromotor noise theory.
"Increased levels of stress negatively impact our brain’s ability to process information," said psychologist Jasmine Kerr, coauthor of the study. "This also affects our motor skills."
Importantly, the heart rates of the stressed individuals didn't differ much from those of their relaxed counterparts. This finding suggests that the monitoring of typing and mousing may actually be a better indicator of increasing stress.
Nägelin and colleagues are now gathering more data by using an app to monitor the computer activity, heart rate and subjective stress levels of office workers. The scientists are quick to point out that a commercial version of the app would have to maintain users' privacy by not recording sensitive data.
A paper on the research was recently published in the Journal of Biomedical Informatics.
Source: ETH Zurich
