Evaluating the effectiveness of online courses in international trade using deep learning

• Published in: PeerJ. Computer science 2024-11, Vol.10, p.e2509, Article e2509
• Main Authors: Zhang, Zhaozhe, Andrés, Javier De
• Format: Article
• Language: English
• Subjects: Algorithms; Deep learning; Distance learning; Education; Educational evaluation; Efficiency; Evaluation; Feedback; Global economy; Implementation effect evaluation; International trade; Machine learning; Methods; Neural networks; Online education; Online instruction; Online international trade course; Students; Study and teaching; Teachers; Technology assessment
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.2509

The development of the world economy has prompted various countries to pay more attention to the teaching of online international trade courses based on deep learning. In the Internet age, online teaching has become an essential way for people to receive education. To guide the public in obtaining high-quality online teaching resources related to international trade, we propose an evaluation method for the implementation of international trade online courses based on deep learning. Firstly, by analyzing the characteristics of online education in international trade courses, we decompose the evaluation methods of online courses in international trade. Then, using deep learning technology, we propose a fusion method of multimodal evaluation features of online courses in international trade. Finally, we design a classification model to realize the effect evaluation of the course by inputting the fused features. Experiments show that our method can accurately evaluate the effect of international trade online courses, with an accuracy of 78.53%.