An Adaptive Recommender System Framework for Personalized E-Learning

Abstract

Due to the gigantic amounts of online learning stuff, e-learning recommender systems are becoming very popular as means of delivering quality content. One of the most common e-learning challenges is to recommend quality of study content to the students. Students have access to a plethora of content or videos for learning various topics, but keeping track of what is relevant to them is a time-consuming task. The present paper focuses on using various recommendation systems and data analytics for personalized learning in an e-learning domain. The paper proposes an adaptive framework for personalized e-learning that solves the problem of previous literature like cold start problem, sparsity problem, over specialization problem etc. The paper also summarized the concepts of eLearning, recommendation systems and data analytics.