Predicting students' learning styles using regression techniques

TL;DR

This paper proposes a regression-based approach to predict students' learning styles, demonstrating that regression models outperform classification models in accuracy, especially when students have multiple or mixed learning styles.

Contribution

The study introduces a probabilistic regression method for learning style detection and compares its effectiveness against traditional classification techniques.

Findings

Regression models are more accurate than classification models.

Regression provides probabilistic insights into multiple learning styles.

Results support using regression for personalized online learning.

Abstract

Traditional learning systems have responded quickly to the COVID pandemic and moved to online or distance learning. Online learning requires a personalization method because the interaction between learners and instructors is minimal, and learners have a specific learning method that works best for them. One of the personalization methods is detecting the learners' learning style. To detect learning styles, several works have been proposed using classification techniques. However, the current detection models become ineffective when learners have no dominant style or a mix of learning styles. Thus, the objective of this study is twofold. Firstly, constructing a prediction model based on regression analysis provides a probabilistic approach for inferring the preferred learning style. Secondly, comparing regression models and classification models for detecting learning style. To ground our conceptual model, a set of machine learning algorithms have been implemented based on a dataset collected from a sample of 72 students using visual, auditory, reading/writing, and kinesthetic (VARK's) inventory questionnaire. Results show that regression techniques are more accurate and representative for real-world scenarios than classification algorithms, where students might have multiple learning styles but with different probabilities. We believe that this research will help educational institutes to engage learning styles in the teaching process.