Classification Accuracy in Cognitive Load for Users Preference in Web based Learning

Abstract

With increasing popularity of web based learning, it is required to design the web layout to reduce cognitive load. Cognitive load theory is widely used to predict the effectiveness of the web based and multimedia learning. The cognitive load induced by instructional and multimedia modes are measured by indirect or subjective methods. Questionnaires are one common form of measuring cognitive load indirectly. In this paper, a questionnaire is prepared to identify the cognitive load of the student and his website preferences in a web learning environment. The cognitive attributes are used as the training input for the Naïve Bayes, Classification Regression Tree(CART), Random Forest and Random Tree for classification. Based on the response of the user, areas for improvement in layout of the web learning system are identified.

Comparison of Decision Tree Methods in Classification of Researcher’s Cognitive styles in Academic Environment

“…According to the experiments, among these four algorithms, Random Forest was the best classifier and predicted accurately with an accuracy of 75%. [5] Also another research is done based on predicting the student's performance which is the major concern to the higher education managements. The dataset was collected among 200 postgarduate students of computer scinence course.…”