Utilizing decision tree machine model to map dental students' preferred learning styles with suitable instructional...

Area of Science:

• Educational Technology
• Machine Learning in Education

Background:

• Student-centered learning (SCL) is increasingly demanded in higher education, but its application in dental education remains limited.
• This study addresses the gap by exploring SCL facilitation in dentistry.

Purpose of the Study:

• To develop an instructional strategy (IS) recommender tool for dental students.
• To map dental students' preferred learning styles (LS) with suitable IS using a decision tree machine learning (ML) technique.

Main Methods:

• A dataset of 255 dental students' learning styles was collected using the modified Index of Learning Styles (m-ILS) questionnaire.
• A decision tree supervised learning model was employed to automate the mapping of LS to IS.
• The accuracy of the developed ML-empowered IS recommender tool was evaluated.

Main Results:

• The decision tree ML model successfully automated the mapping of LS to IS, instantly generating suitable strategies for each student.
• The IS recommender tool achieved perfect precision and recall, indicating high accuracy in matching LS with IS.
• The tool demonstrated good sensitivity and specificity.

Conclusions:

• The decision tree ML-empowered IS recommender tool accurately matches dental students' learning styles with appropriate instructional strategies.
• This tool offers a practical approach for designing student-centered lessons and modules.
• The recommender tool has the potential to significantly enhance the learning experience for dental students.