Li Xuelan, Pei Zhiqiang
School of Management, Anhui Science and Technology University, Bengbu, Anhui, China.
Front Psychol. 2023 Jan 16;13:1111028. doi: 10.3389/fpsyg.2022.1111028. eCollection 2022.
During the COVID-19 pandemic, online learning has become one of the important ways of higher education because it is not confined by time and place. How to ensure the effectiveness of online learning has become the focus of education research, and the role of the "online learning community" cannot be ignored. In the context of the Internet of Things (IoT), we try to build up a new online learning community model: (1) First, we introduce the Kolb learning style theory to identify different online learning styles; (2) Second, we use a clustering algorithm to identify the nature of different learning style groups; and (3) Third, we introduce the group dynamics theory to design the dimensions of the questionnaire and combine the Analytic Hierarchy Process (AHP) method to identify the key influencing factors of the online learning community. We take business administration majors and students in universities as an example. The results show that (1) as a machine learning method, the clustering algorithm method is superior to the random construction method in identifying different learning style groups, and (2) our method can well judge the importance of each factor based on hierarchical analysis and clarify the different roles of factors in the process of knowledge transfer. This study can provide a useful reference for the sustainable development of online learning in higher education.
在新冠疫情期间，在线学习因其不受时间和地点限制，已成为高等教育的重要方式之一。如何确保在线学习的有效性已成为教育研究的焦点，“在线学习社区”的作用不可忽视。在物联网背景下，我们尝试构建一种新的在线学习社区模型：（1）首先，引入科尔布学习风格理论来识别不同的在线学习风格；（2）其次，使用聚类算法来识别不同学习风格群体的性质；（3）第三，引入群体动力学理论来设计问卷维度，并结合层次分析法来识别在线学习社区的关键影响因素。我们以高校工商管理专业及学生为例。结果表明：（1）作为一种机器学习方法，聚类算法在识别不同学习风格群体方面优于随机构建方法；（2）我们的方法能够基于层次分析很好地判断各因素的重要性，并厘清各因素在知识转移过程中的不同作用。本研究可为高等教育在线学习的可持续发展提供有益参考。
