A Study on E-Learner’s Affective-State concerning the Course Complexity in Engineering Education

Abstract

Affective states in learning have gained immense attention in education. The precise affective states prediction can increase the learning gain by adapting targeted interventions which are able to adjust the changes in individual affective states of students. Several techniques are devised for predicting the affective states considering audio, video and bio sensors, but the system that relied on analyzing audio, video cannot certify anonymity and are subjected to privacy problems. This paper devises a novel strategy, namely Rider Squirrel Search Algorithm-based Deep Long Short Term Memory (RiderSSA-based Deep LSTM) for affective state prediction. The training of Deep LSTM is done using proposed RiderSSA. Here, the RiderSSA-based Deep LSTM effectively predicts the affective states like confusion, engagement, frustration, Anger, Happiness, disgust, boredom, surprise, and so on. In addition, the learning styles are predicted based on the extracted features using Rider Neural Network (RideNN) by which the Felder Silverman Learning Style Model (FSLSM) is considered. Here, the RideNN classifies the learners. Finally, the course ID, student ID, affective state, learning style, and the exam score are taken as output data to determine the correlative study. The proposed RiderSSA-based Deep LSTM provided superior performance in contrast to other techniques with highest accuracy of 0.962 and highest correlation of 0.406 respectively.