Developing Empirically Based Student Personality Profiles for Affective Feedback Models

The impact of affect on learning has been the subject of increasing attention. Because of the differential effects of students' affective states on learning outcomes, there is a growing recognition of the important role that intelligent tutoring systems can play in providing affective feedback to students. Although we are only beginning to understand the complex interactions between affect, feedback, and learning, it is evident that affective interventions can both positively and negatively influence learning experiences. To investigate how student personality traits can be used to predict responses to affective feedback, this paper presents an analysis of a large student affect corpus collected from three separate studies. Student personality profiles augmented with goal orientation and empathetic tendency information were analyzed with respect to affect state transitions. The results indicate that student personality profiles can serve as a powerful tool for informing affective feedback models.