Published October 6, 2026 | Version 1

Classifying Students' Learning Styles Using Machine Learning Techniques

  • 1. JNTUH

Description

The classification of students' learning styles plays a pivotal role in enhancing personalized 
education and optimizing teaching methods. This paper explores the application of machine learning 
techniques to accurately classify students' learning styles based on the widely recognized models such as the 
Felder-Silverman Learning Style Model (FSLSM) and the VARK (Visual, Auditory, Reading/Writing, 
Kinesthetic) model. Using datasets derived from student questionnaires, interactions, and behavioral patterns 
in online learning environments, several machines learning algorithms, including Decision Trees, Support 
Vector Machines (SVM), K-Nearest Neighbours (KNN), and Neural Networks, are employed to predict and 
categorize learning styles. Feature engineering techniques are utilized to extract meaningful indicators from 
both behavioural and performance data. The results demonstrate the effectiveness of different algorithms in 
achieving high accuracy rates, with ensemble methods like Random Forests and Gradient Boosting 
outperforming others in most cases. This research contributes to the growing field of adaptive learning by 
offering insights into how machine learning can be leveraged to tailor educational experiences to individual 
learning preferences, enhancing student engagement and academic success. There was an issue retrieving 
recent papers on "Classifying Students' Learning Styles Using Machine Learning Techniques." I will attempt 
a different approach to gather the necessary academic resources and details.

Files

ganga bhavani.pdf

Files (346.2 kB)

Name Size
md5:4533f716378d0438a723e1512efe433f
346.2 kB Preview Download