PROJECT TITLE :

A Fuzzy Tree Matching-Based Personalized E-Learning Recommender System

ABSTRACT:

The rapid development of e-learning systems provides learners with great opportunities to access learning activities on-line, and this greatly supports and enhances the learning practices. But, an issue reduces the success of application of e-learning systems; too many learning activities (like various leaning materials, subjects, and learning resources) are rising in an e-learning system, creating it difficult for individual learners to select correct activities for their specific situations/needs as a result of there's no personalised service operate. Recommender systems, which aim to supply personalised recommendations for products or services, can be used to solve this issue. However, e-learning systems want to be able to handle certain special necessities: 1) leaning activities and learners’ profiles often present tree structures; 2) learning activities contain imprecise and uncertain information, like the unsure categories that the educational activities belong to; 3) there are pedagogical problems, like the precedence relations between learning activities. To deal with the 3 requirements, this study 1st proposes a fuzzy tree-structured learning activity model, and a learner profile model to comprehensively describe the complicated learning activities and learner profiles. Within the two models, fuzzy class trees and connected similarity measures are presented to infer the semantic relations between learning activities or learner necessities. Since it is impossible to own two utterly same trees, in follow, a fuzzy tree matching method is carefully discussed. A fuzzy tree matching-based mostly hybrid learning activity recommendation approach is then developed. This approach takes advantage of each the data-primarily based and collaborative filtering-based mostly recommendation approaches, and considers both the semantic and collaborative filtering similarities between learners. Finally, an e-learning recommender system pr- totype is handy and developed primarily based on the proposed models and recommendation approach. Experiments are done to judge the proposed recommendation approach, and the experimental results demonstrate the nice accuracy performance of the proposed approach. A comprehensive case study concerning learning activity recommendation additional demonstrates the effectiveness of the fuzzy tree matching-based personalized e-learning recommender system in observe.