Predicting Learning and Engagement in Tutorial Dialogue: A Personality-Based Model

摘要: A variety of studies have established that users with different personality profiles exhibit patterns behavior when interacting a system. Although been successfully used to predict cognitive and affective outcomes an interaction, little work has done identify the variations in these based on user profile. In this paper, we model sequences facial expressions, postural shifts, hand-to-face gestures, system interaction events, textual dialogue messages human tutor computer-mediated tutorial session. We use models user's learning gain, frustration, engagement at end particular, examine their Extraversion trait score Big Five Factor survey. The analysis reveals personality-specific are significantly indicative outcomes. These results could impact experience design future interactive systems.