Data Mining with Fuzzy Method Towards Intelligent Questions Categorization in E-Learning

Abstract

These days e-learning has gained a great deal of importance in education and training field. Many universities and colleges are providing online courses through internet. Online examinations with multiple-choice questions are being increasingly used in education system mostly in entrance examinations and competitive examinations. Advantage of online examination is automation in evaluation process and thereby removing the personal bias towards the students. For this purpose, academic institutions are using Learning Management Systems extensively. Moodle, the open-source learning management system is mostly preferred. It is another option to proprietary online learning solutions. In fact, student’s performance cannot be evaluated and assessed only by right and wrong answers in online examination. In proposed experiment an attempt is made to make the examination assessment intelligent. Data mining which is very popularly used in various domains including business but less explored in academic domain. It can be effectively used to mine data generated from e-learning systems. This paper explores the use of data mining algorithm with soft computing technique in question categorization. Proposed work decides the level of difficulty of questions. To categories the questions into different categories like as easy, moderate and tough, fuzzy c-means clustering is used. Along with this, performance of students attempting easy, moderate and tough questions is assessed.