Article: Application of GCN-based teaching path optimisation for teachers in college education Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.52 pp.96 - 116 Abstract: Currently, optimising teachers' teaching paths using graph convolutional networks has become an important exploration direction for improving teaching quality. However, there are still issues with poor model performance and an imperfect evaluation system. To this end, this paper optimises the model algorithm to enhance the research findings of GCN-based optimisation of teaching paths for university teachers. Firstly, this paper explores the potential connections between data by redesigning convolution kernels to adapt to the complex structure of teaching data. At the same time, this paper uses efficient parameter update algorithms such as adaptive moment estimation to dynamically adjust the learning rate based on the first-order and second-order moment estimates of the parameters, in order to accelerate model convergence. The research results indicate that the improved GCN model has an accuracy of 0.97, a precision of 0.96, and a training time of 12 hours when recommending teaching resources. Inderscience Publishers - linking academia, business and industry through research

Title: Application of GCN-based teaching path optimisation for teachers in college education

Authors: Qingsheng Liu

Addresses: School of Education, Huainan Normal University, HuaiNan, 232038, China

Abstract: Currently, optimising teachers' teaching paths using graph convolutional networks has become an important exploration direction for improving teaching quality. However, there are still issues with poor model performance and an imperfect evaluation system. To this end, this paper optimises the model algorithm to enhance the research findings of GCN-based optimisation of teaching paths for university teachers. Firstly, this paper explores the potential connections between data by redesigning convolution kernels to adapt to the complex structure of teaching data. At the same time, this paper uses efficient parameter update algorithms such as adaptive moment estimation to dynamically adjust the learning rate based on the first-order and second-order moment estimates of the parameters, in order to accelerate model convergence. The research results indicate that the improved GCN model has an accuracy of 0.97, a precision of 0.96, and a training time of 12 hours when recommending teaching resources.

Keywords: college education; teaching path optimisation; GCN model; teacher teaching; student development.

DOI: 10.1504/IJICT.2025.151166

International Journal of Information and Communication Technology, 2025 Vol.26 No.52, pp.96 - 116

Received: 25 Sep 2025
Accepted: 22 Oct 2025
Published online: 15 Jan 2026 *

Title: Application of GCN-based teaching path optimisation for teachers in college education

Keep up-to-date