Kastamonu Eğitim Dergisi (Sep 2019)

A Model Proposal to Determine Learning Styles of Students by Using Machine Learning Techniques and Kolb Learning Styles Inventory

  • Elif KARTAL,
  • Sezer KÖSE BİBER,
  • Mahir BİBER,
  • Melodi ÖZYAPRAK,
  • İrfan ŞİMŞEK,
  • Tuncer CAN

DOI
https://doi.org/10.24106/kefdergi.2863
Journal volume & issue
Vol. 27, no. 5

Abstract

Read online

Determining the learning styles in advance plays an important role in the design of the learning environment, in the preparation of the instructor’s course content, and in the learning process of the learner in particular. Kolb’s Learning Style Inventory (KLSI) is one of the most widely used tools to determine learning styles. However, some problems such as misunderstood or unanswered questions can be encountered in application and evaluation stages of the KLSI as in the other questionnaires, scales or psychological tests. The aim of this study is to develop a model proposal for determining learning styles of students by using machine learning techniques and KLSI Version III (KLSI-III) and based on this model to develop an application that can be accessible both online and on mobile devices. For this purpose, data set of this research was created by adding the age and gender attributes to the answers given as the most appropriate option to KLSI-III (unlike Kolb’s original evaluation method). Machine learning techniques such as k-Nearest Neighbor Algorithm, C4.5 Decision Tree Algorithm and Naive Bayes Classifier were applied to this data set and the model with the highest performance has been selected out of this data set. As the application developed within the scope of this study can be easily integrated into e-learning systems; it is thought that it is important for the teachers to facilitate the process of determining the learning styles of the students and accordingly to enable the student-centered design of the training activities and the scientific studies reaching more students.

Keywords