Effectiveness of Relative Evaluation Feedback Using Motivation Tests and Learning Data in University Mathematics

Abstract

This study seeks to improve the performance of students with low motivation and grades in university mathematics. Objective and subjective data were collected simultaneously from e-learning and using motivation tests, respectively, and analyzed by employing machine learning. Then, the results were provided as feedback to learners, which enabled them to undertake self-regulated learning. The results show that post-intervention, the average final exam score is significantly different for the experimental and control groups at 71.9 and 66.2 points, respectively (two-sided t-test; alpha = 0.05; t (89) = 2.35, p = 0.0105). This demonstrates that the feedback provided was helpful for students' learning outcomes. This made it possible to reflect on one's own learning activities by using relative evaluation feedback. This outcome is important in that it can promote self-regulated learning and enable better learning activities.