Research Article
A Personalized Recommendation Method for English Online Teaching Video Resources Based on Machine Learning
@INPROCEEDINGS{10.1007/978-3-031-50549-2_11, author={Hua Sui and Yan Liu}, title={A Personalized Recommendation Method for English Online Teaching Video Resources Based on Machine Learning}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part III}, proceedings_a={ADHIP PART 3}, year={2024}, month={3}, keywords={Machine Learning Online English Teaching Teaching Videos Personalized Recommendation of Resources}, doi={10.1007/978-3-031-50549-2_11} }- Hua Sui
Yan Liu
Year: 2024
A Personalized Recommendation Method for English Online Teaching Video Resources Based on Machine Learning
ADHIP PART 3
Springer
DOI: 10.1007/978-3-031-50549-2_11
Abstract
In order to optimize the utilization of learning resources, provide learners with English online teaching video resources that meet their learning needs and interests, and achieve intelligent recommendation of English online teaching video resources, a machine learning based personalized recommendation method for English online teaching video resources is proposed to address the problem of poor accuracy in personalized recommendation of traditional methods for English online teaching video resources. Using clustering algorithms to classify English online teaching video resources and extract the features of English online teaching video resources. Using graph convolutional neural networks in deep learning to predict users’ preference for English online teaching video resources, obtain recommendation results, and achieve personalized recommendation of English online teaching video resources based on deep learning. The experimental results show that the method has a recommendation accuracy of 92% for 300 users, a video resource recommendation recall rate of 91%, a recommendation path completion rate of 95%, and a recommendation time of 5 s, resulting in better recommendation performance.
