Open AccessAutomatic Detection of Learning Styles: A Decade Review on Data-driven Approaches
Author(s) -
Nor Rahayu Ngatirin,
Zurinahni Zainol
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1997/1/012001
Subject(s) - learning styles , point (geometry) , field (mathematics) , identification (biology) , strengths and weaknesses , style (visual arts) , active learning (machine learning) , computer science , psychology , artificial intelligence , mathematics education , social psychology , history , botany , geometry , mathematics , archaeology , pure mathematics , biology
Different approaches or ways of learning are referred to as learning styles. Learning styles are identified to help educators understand how students learn and to help students become more self-aware of their learning strengths and weaknesses. Students, on the other hand, are unaware of their learning patterns and preferences. The traditional method of determining learning styles has been characterized as a questionnaire-based approach. However, it has various flaws that prohibit learning style identification, such as students' lack of motivation to complete a questionnaire, their reluctance to offer information, and the questionnaire's measurement of learning styles is limited to a single point in time. As a result, an automated approach for automatically detecting students' learning styles has been proposed to overcome these restrictions. The goal of this research is to give a review of existing research in the field of learning styles detection. A total of 36 papers were considered in the study, which was published between 2010 and 2020. Thus, this research highlights the review's findings, which are likely to assist researchers and practitioners in better understanding the theoretical and technical challenges surrounding automatic detection of learning styles.