Aggregating Attention, Emotion, and Cognition Load as Basis for Developing a Rule-based Pedagogy for Online Learner

Abstract

The e-learning system offers an opportunity for educational strategists to monitor the learners' status and improve the teaching-learning outcomes. The study aims to analyze the electroencephalogram (EEG) signal of the learners' attention, emotion, and cognition as determining factors to recommend an appropriate learning pedagogy for every learner. The study analyzed 5,400 data signal datasets with the application of different algorithms to optimize and label the signal classification categories. The data signal components were aggregated as inputs to the regression model. Its resulting p-value determined the prioritization which significantly impacted the learners' learning process. Based on the initial simulation of signal analysis, the study recommends an individualized rule-based pedagogy for each learner, incorporating the EEG instrument to collect the affective and cognitive attributes that can help the learners to adjust better and follow their learning process with minimal supervision of the educational strategist. Likewise, implementing this study in the current e-learning system would provide tremendous learning benefits and improvements in the teaching-learning process.