Assessing Motivational Strategies in Serious Games Using Hidden Markov Models

Recent research has extended tutor strategies to model not just interventions to offer information and activities, but also interventions to support learners’ wills and motivation. It is important to investigate new ways, intertwined with learners’ performance (successful completion of tasks) and judgement (self-report questionnaires), for evaluating tutor intervention strategies. One promising way is the use of physiological sensors. Within this paper, we study some motivational strategies that were implemented in a serious game called HeapMotiv to support learners’ performance and motivation. We build several hidden Markov models which use Keller’s ARCS model of motivation and electrophysiological data (heart rate HR, skin conductance SC and EEG) and are able to identify physiological patterns correlated with different motivational strategies.