Influencing Factors of Students’ Online Learning Satisfaction During the COVID-19 Outbreak: An Empirical Study Based on Random Forest Algorithm

• Published in: Learning Technologies and Systems Vol. 12511; pp. 103 - 114
• Main Authors: Zhang, Yuzhuo, Zhang, Po, Yang, Hongji, Zhao, Kangrui, Han, Chunmei
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: COVID-19; Learning satisfaction; Machine learning; Online learning; Online teaching; Random forest algorithm
• ISBN: 303066905X; 9783030669058
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-66906-5_10

New coronavirus is wreaking havoc around the world and has a profound impact on the international community, especially on higher education. Online teaching provides an effective path for higher education to avoid the risk of cross-contagion in traditional classroom education under epidemic condition. In order to ensure the quality of online teaching during the epidemic, this study takes the students’ satisfaction of online education learning as a measurement object. 1120 online learners from 126 colleges and universities in 26 provinces were investigated through 50 questions survey in 10 dimensions. First, the chi-square test is used to pre-process all the characteristics of the factors, and 30 influencing factors with the highest feature correlation are selected. Random forest algorithm is used to establish a satisfaction classification model in the training set. The accuracy in the test set is 0.72. Through the ranking of feature contribution, the influential factors with higher weight are obtained. The results show that in online learning, the attractiveness of teachers’ teaching methods is the most influential factor, while curriculum arrangement and learning environment rank second and third. Finally, according to the research results, this paper puts forward some suggestions and countermeasures.