Computer mouse movements as a scalable detector of work stress: A longitudinal observational field study

Background: Work stress afflicts individual health and well-being. These negative effects could be mitigated through regular monitoring of employees’ stress. Such monitoring becomes even more important as the digital transformation of the economy implies profound changes of working conditions. Objective: To investigate whether the computer mouse can be used for continuous monitoring and early detection of work stress in the field. Methods: We hypothesized that stress is associated with a speed-accuracy tradeoff in computer mouse movements (CMMs). To test this hypothesis, we conducted a longitudinal field study at a large business organization, where CMMs from regular work activities were monitored over seven weeks (70 subjects, n=1,829 observations). A Bayesian regression model was used to estimate whether self-reported acute work stress was associated with a speed-accuracy tradeoff in CMMs. Results: There was a negative association between stress and the two-way interaction term of mouse speed and accuracy (mean = −0.36, lower = −0.66, upper = −0.08), which means that stress was associated with a speed-accuracy tradeoff. The estimated effect was not sensitive to different processing of the data and remained negative after controlling for the demographics, health, and personality traits of subjects. Conclusions: Self-reported acute stress can be inferred from CMMs, specifically in the form of a speed-accuracy tradeoff. This finding suggests to use regular analysis of CMMs for the early and scalable detection of work stress on the job and thus promises more timely and effective stress management.