An Improved Recommender System for E-Learning Environments to Enhance Learning Capabilities of Learners

Abstract

In the present era to improve learning competence of learners generally every educational organization are adapting e-learning environment. As immense growth of internet and easily accessibility of the World Wide Web it is easier for learners to utilize and acquire benefits through web learning. Educational organizations nowadays adapting personalized e-learning platforms for their learners so as they can progressively get benefited and enhance their learning capabilities. The personalized recommender system helps the learners to overcome information overload problem as learners are recommended e-learning resources according to their habits, likes & dislikes, learning styles, interest area and their level of knowledge.

This paper presents a novel approach, a framework for building architecture for a recommender system for e-learning environment by considering learning style and learners knowledge level. As the learning style and each learners knowledge level is diverse so we should comprehend different needs of the learners and make available them recommendations based on their needs. The proposed approach is based on four modules, first a domain module which contains all the information for a particular area and holds the knowledge about the set of course structure. Second a learner module which contains learners’ personal information, their learning style and their interest area that is uses to identify learners learning preferences and activities. Third an e-assessment module that consists of three blocks named diagnostic assessment, formative assessment and revision module, the main intention of is to provide more benefits to the learners to improve their knowledge. The last module is recommendation module that helps to generate the recommendation of suitable learning module to the learners, founded on their learning style and their level of knowledge. The content-based filtering approach is applied in this module to generate the recommendation which pre-processes data to generate appropriate recommendation list and predicting learners’ performances.