Affective state prediction of E-learner using SS-ROA based deep LSTM

Abstract

An affective state of a learner in E-learning has gained enormous interest. The prediction of the emotional state of a learner can enhance the outcome of learning by including designated mediation. Many techniques are developed for anticipating emotional states using video, audio, and bio-sensors. Still, examining video, and audio will not confirm secretiveness and is exposed to security issues. Here the creator devises a fusion technique, to be specific Squirrel Search and Rider optimization-grounded Deep LSTM for affect prediction.

The Deep LSTM is trained to exercise the new fusion SS-ROA. Then, the SS-ROA-grounded Deep LSTM classifies the states like frustration, confusion, engagement, wrathfulness, and so on. It is based on the interaction log data of the E-learner. In conclusion, the course and student ID, predicted state, test marks, and course completion status are taken as result information to find out the correlations. The new algorithm gives the best performance in comparison to other present methods with the highest prediction accurateness of 0.962 and the most noteworthy connection of 0.379 respectively. After discovering affective states, students may get the advantage of getting real comments from a teacher for improving one's performance during learning. However, such systems should also give feedback about the learner's affective state or passion because it greatly affects the student's encouragement toward better learning.