A Recommender System Assisting Instructor in Building Learning Path for Personalized Learning System

Recent years witnessed a huge demand of personalization in the e-learning system tailoring the learning services based on the characteristics of individual learners. Learner's knowledge, style of learning, and individual preferences play a vital role in offering personalized learning services. Existing learning systems investigated various data mining methods in order to cluster students based on their learning style. These systems cannot provide accurate results using smaller data sets in building models that can generate new clusters based on the historical data. The aim of this paper is to propose a Recommendation system to assist the instructor in identifying the groups of learners who have similar learning styles and provide specialized advices to these clusters of learners. This paper focuses on analyzing the learning styles identified by Felder-Silverman learning style model (FSLSM).