Enhanced Learning Experiences Based on Regulatory Fit Theory Using Affective State Detection

Predicting learners' affective states through the internet has great impact on their learning experiences. Hence, it is important for an intelligent tutoring system (ITS) to consider the learners' affective state in their learning models. This research work focuses on finding learners' frustration levels during learning. Motivating the learners appropriately can enhance their learning experiences. Therefore, the authors also bring in a strategy to respond to learners' affective states in order to motivate them. This work uses Behavioral theory for goal generation, and frustration index is calculated. Based on the frustration level of the learner, motivational messages are displayed to the learners using Regulatory fit theory. The authors evaluated the model using t-test by collecting learners' data from MoodleCloud. The results of the evaluation demonstrate that 80% of the learners' performance significantly increases statistically as an impact of motivational messages provided in response to the learners' frustration.