A MACHINE LEARNING APPROACH TO PREDICT ACADEMIC SUCCESS IN HIGHER EDUCATION USING THE BIG FIVE PERSONALITY TRAITS /
Çağataylı, Mustafa
A MACHINE LEARNING APPROACH TO PREDICT ACADEMIC SUCCESS IN HIGHER EDUCATION USING THE BIG FIVE PERSONALITY TRAITS / Mustafa ÇAĞATAYLI; Supervisor: Assoc. Prof. Dr. Erbug Çelebi - 121 sheets; 31 cm.
Thesis (PhD) - Cyprus International University. Institute of Graduate Studies and Research Management Information Systems Department
Includes bibliography (sheets 91-111)
ABSTRACT Using students' previous course grades is the most common method of forecasting academic performance in higher education. A novel strategy is proposed in this study to predict academic success in higher education using personality traits instead of existing course grades. The primary focus of this multidisciplinary project is to use Machine Learning to combine the benefits of psychology and computer science to predict the academic success of students in higher education institutions. The proposed technique was tested on 20 distinct course categories using Big Five features as personality traits of 2,575 higher education students. We find that Machine Learning may be used to predict academic success while taking into account all five Big Five personality trait dimensions. The Big Five traits of prospective students can be used to predict higher education student achievement for the applied department using our proposed method. Our strategy can be used in a variety of departments or course groups. This approach could be enhanced such that higher education institutions can even recommend departments to students to help them succeed.
Personality--Dissertations, Academic
Education, Higher--Dissertations, Academic
Machine learning--Dissertations, Academic
A MACHINE LEARNING APPROACH TO PREDICT ACADEMIC SUCCESS IN HIGHER EDUCATION USING THE BIG FIVE PERSONALITY TRAITS / Mustafa ÇAĞATAYLI; Supervisor: Assoc. Prof. Dr. Erbug Çelebi - 121 sheets; 31 cm.
Thesis (PhD) - Cyprus International University. Institute of Graduate Studies and Research Management Information Systems Department
Includes bibliography (sheets 91-111)
ABSTRACT Using students' previous course grades is the most common method of forecasting academic performance in higher education. A novel strategy is proposed in this study to predict academic success in higher education using personality traits instead of existing course grades. The primary focus of this multidisciplinary project is to use Machine Learning to combine the benefits of psychology and computer science to predict the academic success of students in higher education institutions. The proposed technique was tested on 20 distinct course categories using Big Five features as personality traits of 2,575 higher education students. We find that Machine Learning may be used to predict academic success while taking into account all five Big Five personality trait dimensions. The Big Five traits of prospective students can be used to predict higher education student achievement for the applied department using our proposed method. Our strategy can be used in a variety of departments or course groups. This approach could be enhanced such that higher education institutions can even recommend departments to students to help them succeed.
Personality--Dissertations, Academic
Education, Higher--Dissertations, Academic
Machine learning--Dissertations, Academic