Research on Learning Resource Recommendation Based on Learner Model

Abstract

In the era of education big data, personalized learning has become the new normal of digital learning. As an important application direction of personalized learning system, learning resource recommendation is used to solve the problems of "information overload" and "information maze" caused by massive learning resources. This paper first constructs learner profile data based on learners' learning behavior, and uses GA-K-means algorithm to cluster learners according to the characteristic data of learner model, which effectively solves the cold start problem caused by untimely resource scoring. Finally, a learning resource recommendation method is designed from the three dimensions of consolidation, promotion and expansion, and N resources with the highest degree of fit are recommended to learners. The experimental results show that GA-K-means algorithm is significantly better than the traditional K-means clustering algorithm in stability and effectiveness, and the classification of learner groups is also in line with the actual situation, which can recommend personalized learning resources that meet the cognitive level for students.