Constructing Intelligent Learning Dashboard for Online Learners

This research is motivated by the growing demand for online learning and the potential of using student-facing intelligent learning dashboards (SF-iLDs) to support online learners. SF-iLDs are designed to increase students' self-regulation, engagement, and course performance by creating visibility into their progress in the online courses. Data visualization and predictive modeling techniques are investigated and integrated into the SF-iLD designed in this study. A predictive model based on the learning management system (LMS) data (generated by both instructors and students) is used to extract and analyze valuable insights about learners' progress in the online courses. The data measures students' learning activities, such as grades on quizzes, assignments, exams, the number of logins, access to the course materials, and the overall course grade. These features are used to classify the learners into three groups: Persistent, Regular, and Irregular. Using this model, the course outcome and the learning gain can be predicted for the students based on their time management and performance in the course activities and assessments. Furthermore, data visualization in the SF-iLD enables students to track their performance in the course, which helps students to better understand their self-regulation ability in the online courses, which potentially influences their self-efficacy and performance in their courses.