Student Behavior Analysis to Predict Learning Styles Based Felder Silverman Model Using Ensemble Tree Method

Abstract

Learning styles are very important to know so that students can learn effectively. By understanding the learning style, students will learn about their needs in the learning process. One of the famous learning management systems is called Moodle. Moodle can catch student experiences and behaviors while learning and store all student activities in the Moodle Log. There is a fundamental issue in e-learning where not all students have the same degree of comprehension. Therefore, in some cases of learning in E-Learning, students tend to leave the classroom and lack activeness in the classroom. In order to solve these problems, we have to know students' preferences in the learning process by understanding each student's learning style. To find out the appropriate student learning style, it is necessary to analyze student behavior based on the frequency of visits when accessing Moodle E-learning and fill out the Index Learning Style (ILS) questionnaire. The Felder Silverman model's learning style classifies it into four dimensions: Input, Processing, Perception, and Understanding. We propose a learning style prediction model using the Ensemble Tree method, namely Bagging and Boosting-Gradient Boosted Tree. Afterwards, we evaluate the classification results using Stratified Cross Validation and measure the performance using accuracy. The results showed that the Ensemble Tree method's classification efficiency has higher accuracy than a single tree classification model.

Closing the gap: exploring the untapped potential of machine learning in deaf students and hearing students’ academic performance

“…The inactivity of users and incompletion of courses are the major issues related to eLearning. It is necessary to understand each student's learning style to know their preferences in the learning process [106]. The data from eLearning activities are used with ML models to detect the learning style of a student.…”

Learning Styles Impact Students’ Perceptions on Active Learning Methodologies: A Case Study on the Use of Live Coding and Short Programming Exercises

“…Isal et al [42] create and assess an adaptive mobile learning application designed to accommodate diverse student needs, with the FSLSM serving as the benchmark for identifying learning styles. Finally, the way to identify the learning style of students is the subject of current research [43][44][45], proposing new methods based on machine learning.…”