Data Using Built-In AI Tools to Identify Engagement Patterns

Abstract

The article reflects the findings of a research conducted to determine behavioral patterns of student engagement depending on the correlation analysis of the digital footprint in the learning management system (LMS) Moodle. Based on one of the courses, Introduction to Information Security, the authors examined the data of 148 students watching video lectures, discussing on a forum, and their academic performance. With the help of integrated analytical tools, some of the main indicators of effective learning, including; thoughtful viewing, early participation in discussion and social engagement, were revealed. The methods of statistical analysis such as Pearson correlation and the t-test have shown significant associations between these markers and the end of course score. Depending on the obtained results, recommendations are formulated in practice to streamline the learning process, such as the use of interactive work with lectures and active involvement in discussions in such forums. The research proves the possibility of utilizing educational analytics and data mining to enhance the quality of education and facilitate the process of making pedagogical choices.