Using analytics to predict students' interactions with learning management systems in online courses

In online education, it is widely recognized that interaction and engagement have an impact on students' academic performance. While previous research has extensively explored interactions between students, instructors, and content, there has been limited exploration of course design elements that promote the fourth type of interaction: interaction between students and the Learning Management System (LMS). Considering the connection between these interactions and students' academic achievements, this study aims to bridge this gap in the existing literature by investigating the factors that can predict learner-LMS interactions. By analyzing LMS analytics and log data collected from 5,114 participants in an online computer science course, this quantitative study utilized a combination of Multiple Linear Regression (MLR) and Decision Tree (DT) to predict learner-LMS interactions. The chosen model, trained on 80% of the dataset and tested on the remaining 20%, demonstrated effectiveness. The findings highlight the power of the selected model in predicting learner-LMS interactions. Key predictors include students' average submissions, average minutes, average content accesses, and average assessment accesses. Based on these key factors, the discussion provides insights for optimizing course design in online learning experiences.