Shara M. Baylin^1,, Laila S. Lomibao¹

Academic procrastination appears to be widespread among university students. They delay in writing and turning in their assignments, presentations, and other academic requirements. Academic performance suffers as a result of incomplete and delayed assignments. This paper investigated the use of educational data mining techniques for the early detection of academic procrastination tendencies in online mathematics learning. Data are collected first-hand by the researchers using the research instruments. The features selected in this study were data that can be easily gathered even in the first week of school, and thus fits more for a model to predict as early as possible. The study was conducted among mathematics education students at the University of Science and Technology of Southern Philippines – CDO Campus. The K-means clustering method was used in the study to group students who procrastinate and Filter-based methods, particularly Information Gain (IG), Gain Ratio (GR), Gini Decrease (GD), Chi-square, and ReleifF were used to identify the most informative features that contribute most significantly to student performance, learning outcomes, or other relevant educational metrics. The results revealed that 5 of the identified features are relevant in predicting students’ procrastination tendencies and the Gaussian-Bernoulli Mixed Naïve Bayes model can successfully predict students’ later procrastination behaviors with a testing accuracy of 85% and Kappa score of 82%. Mathematics educators and administrators can use this model to predict and prevent the negative consequences of students' academic procrastination.

academic procrastination, educational data mining, online learning, procrastination