Design of Online English Teaching Resource Recommendation Method Based on Light GCN-CSCM Model

Abstract

Based on the Light GCN-CSCM model, this study for recommending online English. With the popularity of the Internet, online English teaching platforms are booming, but learners still face challenges in choosing the right content from numerous resources. This study aims using social network information, combined with the Light GCN-CSCM model, to achieve accurate and personalized English teaching resource recommendations. This paper introduces the principle of the Light GCN-CSCM model and applies it to online English teaching resource recommendations. Methods such as data preprocessing, model realization, integration and optimization of the recommendation system are designed, and appropriate evaluation indexes are selected for evaluation. The effectiveness and performance advantages of the proposed method are verified by experiments on real data sets. The Light GCN-CSCM model-based online English teaching resource recommendation method has achieved significant improvement in the accuracy of personalized recommendations and user satisfaction. This study constructed an efficient recommendation system by in-depth analyzing the characteristics of online English teaching resources and the needs of users. This system can provide customized teaching resources for users based on their learning habits, levels, and interests, greatly improving the pertinence and efficiency of learning.