Predicting Learner's Affective States from a Dialogue with AutoTutor

This research attempts to validate the hypothesis that learner's affective states can be predicted from relevant features of a natural language dialogue with AutoTutor. After a learning session with AutoTutor, the affective states of the learner were classified by the learner, a peer, and two trained judges. Multiple regression analyses revealed that conversational features significantly predicted boredom, confusion, flow, and frustration, but not delight and surprise.