Prediction of Learner's Profile Based on Learning Styles in Adaptive E-learning System

Abstract

The major requirement of e-learning system is to provide a personalized interface with personalized contents which adapts to the learning styles of the learners. This is possible if the learning styles of the learner is known. In this paper, it is proposed to identify the learning styles of the learner, by capturing the learning behavior of the learner in the e-learning portal using Web Log Mining. The learning styles are then mapped to Felder-Silverman Learning Style Model (FSLSM) categories. Each category of the learner is provided with the contents and interface which are apt for that category. Fuzzy C Means (FCM) algorithm is used to cluster the captured learning behavioral data into FSLSM categories. The learning styles of a learner get changed over a period of time hence the system has to adapt to the changes and accordingly provide the necessary interface and contents. For this, the Gravitational Search based Back Propagation Neural Network (GSBPNN) algorithm is used to predict the learning styles of the learner in real-time. This algorithm is a modification of basic Back Propagation Neural Network (BPNN) algorithm which calculates the weights using Gravitation Search Algorithm (GSA). The algorithm is validated on the captured data and compared using various metrics with the basic BPNN algorithm. The result shows that the performance of GSBPNN algorithm is better than BPNN.