Automatic Recommendation Technology for Learning Resources with Convolutional Neural Network

Abstract

Automatic learning resources recommendation has become an increasingly relevant problem: it allows students to discover new learning resources that matches their tastes, and enables e-learning system to target their learning resources to the right students. In this paper, we propose an automatic learning resources recommendation algorithm based on convolutional neural network (CNN). The CNN can be used to predict the latent factors from the text information. To train the CNN, its input and output should be solved firstly. For its input, the language model is employed. For its output, we propose the latent factor model, which is regularized by L1-norm. Furthermore, the split Bregman iteration method is introduced to solve the model. The major novelty of the proposed recommendation algorithm is that a new CNN is constructed to make personalized recommendations. Experimental results on public database in terms of quantitative assessment show significant improvements over conventional methods. Especially, it can also work well when the existing recommendation algorithms suffer from the cold-start problem.