Wang, Shaoyi; Xu, Yan; Li, Quanlong; Chen, Yuanlong
Learning Path Planning Algorithm Based on Learner Behavior Analysis Proceedings Article
In: 2021 4th International Conference on Big Data and Education, S. 26–33, Association for Computing Machinery, New York, NY, USA, 0000, ISBN: 9781450389389.
Abstract | Links | BibTeX | Schlagwörter: Learning path, O, Smart education, Time series
@inproceedings{Wang2021,
title = {Learning Path Planning Algorithm Based on Learner Behavior Analysis},
author = {Shaoyi Wang and Yan Xu and Quanlong Li and Yuanlong Chen},
url = {https://doi.org/10.1145/3451400.3451405},
doi = {10.1145/3451400.3451405},
isbn = {9781450389389},
booktitle = {2021 4th International Conference on Big Data and Education},
pages = {26–33},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICBDE 2021},
abstract = {Internet online education platforms are developing at an unprecedented speed. Ordinary people can also have zero-distance access to excellent courses from excellent universities that were inaccessible in the past. However, learners are unable to quickly find content that suits their learning interests and abilities in the massive learning materials, resulting in greatly reduced learning effects. This article conducts research on how to fill the knowledge gap between learners and educational resources, and aims to plan individualized and highly compatible learning paths for learners. Combining the prediction results of the exercises and answering questions, the knowledge points and courses are modeled. Based on the established model, a learning path planning algorithm with review strategies based on the knowledge graph is proposed, and the topological sorting is used to show the completeness for the learners at the end. Personalized learning path. The experimental results show that the method has satisfactory accuracy. It can provide learners with a personalized learning path.},
keywords = {Learning path, O, Smart education, Time series},
pubstate = {published},
tppubtype = {inproceedings}
}
Internet online education platforms are developing at an unprecedented speed. Ordinary people can also have zero-distance access to excellent courses from excellent universities that were inaccessible in the past. However, learners are unable to quickly find content that suits their learning interests and abilities in the massive learning materials, resulting in greatly reduced learning effects. This article conducts research on how to fill the knowledge gap between learners and educational resources, and aims to plan individualized and highly compatible learning paths for learners. Combining the prediction results of the exercises and answering questions, the knowledge points and courses are modeled. Based on the established model, a learning path planning algorithm with review strategies based on the knowledge graph is proposed, and the topological sorting is used to show the completeness for the learners at the end. Personalized learning path. The experimental results show that the method has satisfactory accuracy. It can provide learners with a personalized learning path.