A New Approach of an Intelligent E-Learning System Based on Learners' Skill Level and Learners' Success Rate

Introduction

Traditionally, the courses in e-learning systems consist of static hypertext pages with no student adaptability (Ghali et al., 2008). However, since the 1990s, researchers began to incorporate adaptability into their systems. Intelligent e-learning systems (IES) are distance educational systems based on the Internet. One of the main problems in IES is to determine how to adapt the curriculum sequence to each student according to their learning characteristics (Kahraman, 2009) (Brusilovsky et al., 2003). At present, most of the studies on e-learning either concentrate on technological aspect or focus on adapting learner’s interests or browsing behaviors, while, learner’s skill level and learners’ success rate is usually neglected. Generally, inappropriate courseware leads to learner cognitive overload or disorientation during learning processes, thus reducing learning performance (Cobos et al., 2013; Ghadirli et al., 2013). Besides, the learning paths problem of concept continuity also needs to be considered while implementing personalized courseware generation because smoother learning paths increase learning performance, avoiding unnecessary difficult concepts.

In this paper, learners’ skill level and learners’ success rate are used as valuable information to represent learner’s current state and modify the difficulty level of each course material, in order to update the courseware material sequence. Courseware material sequencing aims to provide an optimal learning path to individual learner since every learner has different prior background knowledge.

The rest of the paper is organized as follows: section 2 provides the literature review on cognitive load theory and intelligent e-learning systems. In Section 3 we will give an overview on the overall architecture of the intelligent e-learning system. Section 4 will describe the scope of our approach. The experiments that have been conducted will be presented in Section 5. Section 6 will discuss the results of the experiment. We will conclude the paper in Section 7 along with the further works of the study.