DNN-Based Modeling of Ideological and Political Resource Recommendation for Higher Education

Abstract

The rapid development of online learning platforms has led to resource overload and mismatches between learners and educational content in higher education, creating an urgent need for systematic and intelligent recommendation systems for ideological and political education. This paper proposes a deep neural network–based method for modeling and designing an information system for personalized learning resource recommendation. The approach learns unified latent representations of learners and resources by capturing complex nonlinear interactions from multidimensional behavioral data, thereby ensuring semantic alignment between learning needs and educational content. Experiments conducted on real-world datasets demonstrate that the proposed method outperforms traditional approaches in terms of prediction accuracy and recommendation stability. This study contributes to model-driven system development and intelligent information system design in educational settings, providing a feasible solution for adaptive learning services.