The Recommendation System of Innovation and Entrepreneurship Education Resources in Universities Based on Improved Collaborative Filtering Model

Abstract

In the huge number of online university education resources, it is difficult for learners to quickly locate the resources they need, which leads to “information trek.” Traditional information recommendation methods tend to ignore the characteristics of learners, who are the main subjects of education. In order to improve the recommendation accuracy, a recommendation algorithm based on improved collaborative filtering model is proposed in this paper. Firstly, according to the student behavior data, consider the behavior order to create the behavior graph and behavior route. Then, the path of text type is vectorized by the Keras Tokenizer method. Finally, the similarity between multidimensional behavior path vectors is calculated, and path collaborative filtering recommendations are performed for each dimension separately. The MOOC data of a university in China are introduced to experimentally compare the algorithm of the article as well as the control group algorithm. The results show that the proposed algorithm takes better values in evaluation indexes, thus verifying that this algorithm can improve the effectiveness of innovation and entrepreneurship education resources recommendation in universities.

Prediction of Students’ Grade by Combining Educational Knowledge Graph and Collaborative Filtering

“…The method proposed in this paper is inspired by the application of knowledge graphs in recommendation systems, generally speaking, the use of knowledge graphs in prediction and recommendation methods is to expand semantic information.For example, Geng L [17]created behavior graphs and behavior paths based on the historical behavior sequences of learners, calculating the similarity between paths, using path-based collaborative filtering to predict user behavior and make recommendations.Hongwei, et al [18]Established a movie knowledge graph, utilizing the information in the knowledge graph for convolution to predict user interests and recommend movies. Knowledge Graph Convolutional Networks (KGCN) is an end-to-end framework that effectively captures the inter-item relatedness by mining their associated attributes on the knowledge graph, thereby alleviating data sparsity and cold-start issues.…”

Research on quality evaluation of innovation and entrepreneurship education for college students based on random forest algorithm and logistic regression model

“…A novel ML based system is proposed by Jiang & Li (2021) that considers the curriculum, teaching and training modes, reforms in practice and teaching in I&E. An intelligent strategy to assess the performance is designed using SVM, Extreme Learning Machines (ELM) and Radia Basis Function (RBF) that uses the facial expressions of the students. An improved collaborative filtering model that uses behavior graph and route of students to assess the performance of EE ( Geng, 2022 ). This path is and the multidimensional behavior path is analysed for extracting the similarities between each dimension.…”

Improving Collaborative Filter Using BERT

“…It demonstrates that the proposed algorithm has greater advantages in three evaluations. If the size of the database had been higher, they would have been able to achieve far more successful outcomes [6].…”