Discrete Dynamic Modeling Analysis Based on English Learning Motivation

With the popularization of the Internet, various online learning platforms have developed rapidly, providing users with abundant learning resources, and realizing personalized resource recommendation has become the development trend of online learning platforms. In this paper, a personalized learning recommendation model based on improved collaborative filtering is proposed. Firstly, a multilayer interest model of learners is established to accurately describe learners’ interest in knowledge topics, courses, and knowledge areas; then, in view of the sparse scoring matrix and cold-start problems of traditional collaborative filtering recommendation algorithms, an improved collaborative filtering-based personality is proposed. The personalized learning recommendation model is used to improve the similarity calculation of users by introducing user initialization tags and solve the cold-start problem of new users. Finally, the effectiveness of the algorithm is proved by experimental comparison, and the improved algorithm improves the recommendation effect of personalized learning.