• search hit 9 of 645
Back to Result List

Unveiling the secrets of learning styles: decoding eye movements via machine learning

  • Universities are faced with a rising number of dropouts in recent years. This is largely due to students' limited capability of finding individual learning paths through various course materials. However, a possible solution to this problem is the introduction of adaptive learning management systems, which recommend tailored learning paths to students – based on their individual learning styles. For the classification of learning styles, the most commonly used methods are questionnaires and learning analytics. Nevertheless, both methods are prone to errors: questionnaires may give superficial answers due to lack of time or motivation, while learning analytics do not reflect offline learning behavior. This paper proposes an alternative approach to classify students' learning styles by integrating eye tracking in combination with Machine Learning (ML) algorithms. Incorporating eye tracking technology into the classification process eliminates the potential problems arising from questionnaires or learning analytics by providing a more objective and detailed analysis of the subject's behavior. Moreover, this approach allows for a deeper understanding of subconscious processes and provides valuable insights into the individualized learning preferences of students. In order to demonstrate this approach, an eye tracking study is conducted with 117 participants using the Tobii Pro Fusion. Using qualitative and quantitative analyses, certain patterns in the subjects' gaze behavior are assigned to their learning styles given by the validated Index of Learning Styles (ILS) questionnaire. In short, this paper presents an innovative solution to the challenges associated with classifying students' learning styles. By combining eye tracking data with ML algorithms, an accurate and insightful understanding of students' individual learning paths can be achieved, ultimately leading to improved educational outcomes and reduced dropout rates.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Dominik BittnerORCiD, Timur EzerORCiD, Lisa GrabingerORCiD, Florian HauserORCiD, Jürgen MottokORCiDGND
DOI:https://doi.org/10.21125/iceri.2023.1291
ISBN:978-84-09-55942-8
Parent Title (English):Proceedings of the 16th annual International Conference of Education, Research and Innovation (ICERI 2023), Seville, Spain, 11/13/2023 - 11/14/2023
Publisher:IATED
Editor:Luis Gómez Chova, Chelo González Martínez, Joanna Lees
Document Type:conference proceeding (article)
Language:English
Year of first Publication:2023
Release Date:2023/12/14
First Page:5153
Last Page:5162
Institutes:Fakultät Elektro- und Informationstechnik
Fakultät Elektro- und Informationstechnik / Laboratory for Safe and Secure Systems (LAS3)
research focus:Digitalisierung
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG