基于学习分析的在线学业成就影响因素研究

A Research on Online Learning Achievement Factors Based on Learning Analysis

如何利用数据和模型来预测学业成功与失败是学习分析领域的核心问题。该文通过对现有文献检索分析出目前研究中主要影响学业成就的要素,结合对原始数据的深度处理,得到和学习相关的高级行为指标,利用机器学习中神经网络、决策树及线性回归算法分别建模分析。研究发现:学习态度、学习及时水平和投入水平是影响在线学业成就的主要因素,耐挫水平为次要因素,而互动水平、积极水平和阶段成效对最终的学业成就无关。该文最后对研究结果进行了反思后认为,课程选取对研究在线学业成就要素有非常大的影响。

How to use data and models to predict the success and failure of learning is the core problem in the field of learning analysis. Around this theme, domestic and foreign scholars have carried out a lot of research from the aspects of theoretical discussion, framework analysis, etc., and a few scholars have conducted relevant empirical research based on questionnaires or online raw data. The main research methods are regression analysis or structural equation modeling. This paper analyzes the main factors that affect academic achievement in the present research by searching the existing literatures, and gets the advanced behavioral index of the study through the deep processing of the original data. By using neural network, decision tree and linear regression algorithm in machine learning to model and analyze, it is found that learning attitude, Timeliness level and involvement level are the main factors that affect the online academic achievement, while the level of resistance to frustration is the secondary factor. However, the level of interaction, the level of positivity and the level of stage achievement are not related to the final academic achievement. Finally, it is found that the curriculum selection has a great impact on the study of online academic achievement factors.