Differentiated Instructional Content Classification Using Student Modelling Approach

Abstract

The student model plays a main role in planning the training path, supplying feedback information to the pedagogical module of the system in an Intelligent Tutoring System. Student model is the preliminary component, which stores the information about the specific individual learner. In this study, neural network and psychometric analysis captured the student capabilities in a Physics domain in a technology- enabled active learning environment to create a rich interactive learning experience. 415 training sessions from 105 Pre-University Students were tested in this Student Modelling System, to capture their input via Multiple Choice Questions where the student's results were subjected to neural network and psychometric interventions. This is because neural networks can bring psychometric and econometric approaches to the measurement of attitudes and perceptions. Added to it, the differentiated instructional content classification lets the students to ponder upon the learning content based on their ability, rather than tumbling upon the content, which are far beyond their ability and learning reach. The result of this research showed a positive classification of students based on their capability. Looking at the overall percentage of misclassificaiton and that of the correctly predicted group members, the discriminating function gives the acuracy of the model to be presisely at 79.8%. Thus, this research seems to pave way to all the Physics facilitators, who wish to adopt differentiated instruction using student-modelling approach.