Monitoring mental stress through mouse behaviour and decision-making patterns

Abstract

More and more technological advances offer new paradigmsfor training, allowing novel forms of teaching and learning to be devised.A widely accepted prediction is that computing will move to the back-ground, weaving itself into the fabric of our everyday living spaces andprojecting the human user into the foreground. This forecast turns outto be an opportunity for human-computer interaction as a way to mon-itor and assess the user’s stress levels during high-risk tasks. The maineffects of stress are increased physiological arousal, somatic complaints,mood disturbances (anxiety, fear and anger) and diminished quality ofworking life (e.g. reduced job satisfaction). To mitigate these problems,it is necessary to detect stressful users and apply coping measures tomanage stress. Human-computer interaction could be improved by hav-ing machines naturally monitor their users’ stress, in a non-invasive andnon-intrusive way. This article discusses the development of a randomforest classifier with the goal of enabling the assessment of high schoolstudents’ stress during academic exams, through the analysis of mousebehaviour and decision-making patterns.