ABSTRACT
Academic achievement is an important factor strongly related to positive educational experiences that facilitate subsequent learning. Therefore, identifying students who need support at an early stage and promptly providing appropriate intervention play a crucial role in preventing learning deficits. This study examined the longitudinal change in elementary school students’ proficiency status to understand the nature of longitudinal transitions. It explored the feasibility of developing early predictive models for identifying students potentially facing academic difficulties based on information obtained from elementary school. Deep neural network and hierarchical generalized linear models were applied to large-scale national assessment panel data collected within the framework of an accountability system in South Korea. The results showed that although most students maintained their initial proficiency status, a substantial number of students made longitudinal transitions from non-proficiency to proficiency or vice-versa as they progressed from elementary to high school. The predictive models had an acceptable level of accuracy in predicting future academic performance, considering the degree of student mobility across proficiency levels over grades. The study concluded that the predictive models can serve as a starting point to identify students who need assistance and provide educators with a means to intervene promptly.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Hyun Sook Yi
Hyun Sook Yi is a professor in the Department of Education at Konkuk University, South Korea, where she teaches educational assessment, evaluation policy, and educational statistics. Her earlier work has focused on applying educational measurement and statistics theories to large-scale assessment and investigating issues related to test development and estimation of student performance. Her current research interests include application of measurement and statistical models such as cognitive diagnostic modelling and structural equation modelling in K-12 education settings and prediction of cognitively and emotionally at-risk students. She recently published an article on application of an artificial neural network model in predicting and identifying academically at-risk students using the Korea National Assessment of Educational Achievement.
Wooyoul Na
Wooyoul Na is a Ph.D. candidate and research assistant in the Department of Education at Konkuk University, South Korea. He holds a Master’s degree in Counseling Psychology and currently in the educational measurement program. He is interested in applying educational measurement and statistics theories in the field of counselling psychology and recently published articles on longitudinal analyses of high school students’ dropout, school violence, and characteristics of run-away adolescents.
Changmook Lee
Changmook Lee is a learning scientist and leader of the AI modelling team in Woongjin Thinkbig Co., Ltd., South Korea. He holds a Doctoral degree in Measurement and Statistics and is interested in computer-aided systems, intelligent tutoring systems, and AI in education. He recently developed an AI core of personalized adaptive learning systems for elementary maths operations which can measure learner’s mastery status and provide proper interventions to enhance engagement.