Prioritization of e-learners activities using principal component analysis method

Abstract

In recent years, E-learning has transformed teaching and learning pedagogy. Unlike traditional teaching, E-learning is more of student-centred learning and is based on learning activities. Researchers have evolved with the most suitable e-learning activities to consider while designing any virtual course. However, adapting to online activities and achieving the desired learning outcome varies from learner to learner. It is generally observed that the learners attain the learning outcome much faster if guided with their preferred learning activities. Thus, identifying the most preferred learning activities of a learner will ensure quicker learning capacities. The existing methods tend to streamline the learners into visual, auditory, and kinaesthetic types, however, the learning activities of a learner are not prioritized, which is addressed in this paper. If, the set of learning activities is represented in n dimensions, reducing the n dimensions to a fewer dimension is required. Out of the existing dimensionality reduction methods, principal component analysis (PCA) best reduces the dimensions while preserving the integrity of the data set. PCA achieves this by computing principal components which are uncorrelated variables maximizing the variance. In this paper, we propose an algorithm to identify one of the most preferred learning activities of learners through the application of the PCA method, and then the prioritization of the learning activities will be compared with the Pearson correlation co-efficient method for the accurateness of the suggested algorithm.