Student Engagement Dataset (SED)

Distance learning has become a popular medium of education with the spread of the internet since the early 2000s. To leverage this phenomenon, learning analytics and data mining can provide insights for improving pedagogy and assessing student engagement. To that end, a student centric dataset was constructed by extracting data from the Universiti Malaya’s Moodle-based Virtual Learning Environment (VLE), serving approximately 25,000 students annually. In this paper, we present the Student Engagement Dataset (SED). The dataset consists of 16,609 students and 2,407 courses. It contains information such as their grades and daily logged online activities (approximately 12 million data points) including temporal data represented across 4 tables. Included in the tables is a table of student engagement features, created by aggregating the raw activity data. Here, we present the properties of the dataset and describe the data collection, data selection, and the processing steps we undertook. Correlation analysis on the student engagement features shows that there is a statistically significant but weak negative correlation between the number of courses, early morning login and the number of assignments with the performance of top students. It is hoped that SED will present new opportunities for researchers in the learning analytics domain.