The way people type and click on the computer is a better way to detect stress than heart rate, according to a study published in the Journal of Biomedical Informatics.
In Switzerland — and probably all around the world — one in three employees suffers stress related to their work. Many don’t even realise how much it’s affecting them until it’s too late. This makes it all the more important to identify stress as early as possible to avoid long-term consequences.
Now, a team of researchers from ETH Zurich is taking an important step to detect work-related stress. Using machine-learning tools, they developed a model that can identify stressed workers by how they type on the computer. “How we type on our keyboard and move our mouse seems to be a better predictor of how stressed we feel in an office environment than our heart rate,” explained study author Mara Nägelin, a mathematician who conducts research at the Chair of Technology Marketing and the Mobiliar Lab for Analytics at ETH Zurich. The team believes these findings could be used to detect stress early in the workplace.
In this study, ETH researchers showed how stressed people type or use their computer mouse differently compared to more relaxed people. “People who are stressed move the mouse pointer more often and less precisely and cover longer distances on the screen. Relaxed people, on the other hand, take shorter, more direct routes to reach their destination and take more time doing so,” said Nägelin.
What’s more, if they’re stressed, people make more mistakes when typing. They tend to write abruptly with many stops and starts. In contrast, relaxed people write more consistently with fewer pauses when typing on a keyboard.
The authors explain that the neuromotor noise theory can explain the link between stress and typing. “Increased levels of stress negatively impact our brain’s ability to process information. This also affects our motor skills,” explained psychologist Jasmine Kerr, coauthor in the study.
To study stress levels, ETH researchers observed 90 participants completing office tasks, such as planning meetings or analysing data. To mimic a real office environment, some participants were frequently interrupted by chat messages and had to participate in an interview, while others were allowed to work in silence. They recorded mouse movements and keyboard strokes, as well as their heart rate. In addition, the team also asked participants how stressed they felt. “We were surprised that typing and mouse behaviour was a better predictor of how stressed subjects felt better than heart rate,” Nägelin says.
The team is now testing their model further afield, with more participants working in real offices. However, the authors caution about abusing this data. “The only way people will accept and use our technology is if we can guarantee that we will anonymise and protect their data. We want to help workers to identify stress early, not create a monitoring tool for companies,” concluded Kerr.
Naegelin M, Weibel RP, Kerr JI, Schinazi VR, La Marca R, von Wangenheim F, Hoelscher C, Ferrario A. An interpretable machine learning approach to multimodal stress detection in a simulated office environment. J Biomed Inform. 2023 Mar;139:104299. doi: 10.1016/j.jbi.2023.104299. Epub 2023 Jan 30. PMID: 36720332.