Research on Learning Evaluation of Online General Education Course Based on BP Neural Network

• Published in: Computational intelligence and neuroscience Vol. 2021; no. 1; p. 3570273
• Main Author: Zhang, Zongbiao
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc; Hindawi Limited
• Subjects: Academic achievement; Analysis; Back propagation networks; CAI; China; Colleges & universities; Computer assisted instruction; Curricula; Curriculum; Distance learning; Economic reform; Education; Education reform; Education, Distance; Educational evaluation; Higher education; Internet; Learning; Neural networks; Neural Networks, Computer; Online education; Online instruction; Standard deviation; Structural analysis; Students; Universities; Validity; Variables; China
• ISSN: 1687-5265; 1687-5273
• DOI: 10.1155/2021/3570273

Network open curriculum provides a new solution for general education in local colleges and universities, which makes the network curriculum widely popularized and applied in colleges and universities. However, due to the lack of good curriculum learning evaluation, it is inconvenient for learners to choose. Therefore, this paper proposes to use the BP neural network model to evaluate the learning process of network general education course. Based on the course and user data provided by the existing platform, this paper constructs an online course learning evaluation model and studies the structure and effect relationship among learning experience, learning investment, and learning performance of ordinary online courses based on the preaging process product (3P) model and structural analysis method. Our research shows that curriculum quality is a key factor in analyzing and predicting learning results, which has a great impact on learning achievement. Learning experience is a direct factor affecting academic achievement. Learning experience, as an intermediary variable, indirectly affects e-learning performance. At the same time, it puts forward some suggestions to optimize the learning effect of ordinary online courses. On the one hand, the evaluation model provided in this paper can provide a reference for learners to select online courses; on the other hand, it can also be used as a supplement to the existing subjective evaluation model.