A Study on the Development of a Customized Preventive Counseling Support Model for Students Based on Big Data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aims to develop a predictive model for student counseling support by identifying key individual factors encountered in university life, such as academic performance, financial conditions, psychological factors, and campus environment, as explanatory variables. Using logistic regression (logit model), the model was constructed to predict academic persistence and dropout, set as binary response variables, and validated for consistency through the support index. Additionally, the consistency of the dropout prediction model based on the logit model was cross-validated using a classification model with CART (Classification and Regression Tree) to determine which model or approach provided superior results. Modeling and comparing 2,000 simulated data points yielded similar results. All explanatory variables, except gender, were significant (p < .05), and, considering odds ratios, the number of leaves of absence (1.7818) and academic warnings (1.2921) had strong positive effects on dropout likelihood. Conversely, academic year, number of enrolled semesters, and GPA showed a negative effect on dropout probability. From a practical perspective for system implementation and operation, the logit model proved more efficient for constructing and applying the prediction model.
Abstract
This study aims to develop a predictive model for student counseling support by identifying key individual factors encountered in university life, such as academic performance, financial conditions, psychological factors, and campus environment, as explanatory variables. Using logistic regression (logit model), the model was constructed to predict academic persistence and dropout, set as binary response variables, and validated for consistency through the support index. Additionally, the consistency of the dropout prediction model based on the logit model was cross-validated using a classification model with CART (Classification and Regression Tree) to determine which model or approach provided superior results. Modeling and comparing 2,000 simulated data points yielded similar results. All explanatory variables, except gender, were significant (p < .05), and, considering odds ratios, the number of leaves of absence (1.7818) and academic warnings (1.2921) had strong positive effects on dropout likelihood. Conversely, academic year, number of enrolled semesters, and GPA showed a negative effect on dropout probability. From a practical perspective for system implementation and operation, the logit model proved more efficient for constructing and applying the prediction model.
참고문헌 (18)
- Choi, Mi Kyung, "Study of Child Abuse Families Using Logistic Regression Models", Journal of the Korean Data & Information Science Society, 27(5), pp.1327~1336 (2016)
- Chung, Jae Young, "An Analysis of Institutional Factors Affecting on College Dropout Rates", Asian Journal of Education, 16(4), pp.57~76 (2015)
- Han, Jun Tae, "Developing the Credit Risk Scoring Model for Overdue Student Direct Loan", Journal of the Korean Data & Information Science Society, 27(5), pp.1293~1305 (2016)
- Han, Song I., "Exploration of Factors that Affect College Student Drop-out and Resilience", Journal of Learner-Centered Curriculum and Instruction, 18(24), pp.1369~1391 (2018)
- Hwang, Young Sik, "The Effect of Educational Environment in University to the Dropout Rate of Attending Students", Educationl research, 84, pp.109~128 (2022)
- Kang, Myunghee, "Trends and Influencing Factors of College Students’Dropout Intention", Forum for Youth Culture, 58, pp.5~30 (2019)
- Kang, Seung-Ho, "Predictors of Academic Achievement and Dropout Thinking among University Students", Journal of Educational Evaluation, 23(1), pp.29~53 (2010)
- "Statistical Yearbook of Education" (2024)[URL]
- Lee, Eun Hwa, "The Research Trends and Implications of College Dropouts in Korea", The Journal of Learner-Centered Curriculum and Instruction, 19(10), pp.169~199 (2019)
- Lee, Eun Jung, "An Exploratory Study on Determinants Predicting the Dropout Rate of 4-year Universities Using Random Forest : Focusing on the Institutional Level Factors", Journal of Educational Technology, 36(1), pp.191~219 (2020)
- Lee, Young Ae, "A Study on the Developing Character Education Program for Prevention from Dropouts", The Korean Journal of East West Mind Science, 9(1), pp.95~104 (2006)
- Lim, Eon, "College Students’ Leave of Absence Types and Related Factors", The Journal of Vocational Education Research, 30(2), pp.231~248 (2011)
- Park, Eun Sun, "Effects of the Factors of Academic Suspension and College Adjustment on the Intention of College Freshmen’s School Dropouts", Korean Journal of Youth Studies, 23(10), pp.361~384 (2016)
- Park, Il Su, "Developing the High-risk Drinking Predictive Model in Korea Using the Data Mining Technique", Journal of the Korean Data & Information Science Society, 28(6), pp.1337~1348 (2017)
- Shin, Hee Geon, "A Study on Development of Support Index for Supporting Adaptive and Preventive Counseling Based on Logit Model", Journal of the Korean Data & Information Science Society, 30(2), pp.323~333 (2019)
- Stoecker, J., "Persistence in Higher Education : A 9-year Test of a Theoretical Model", Journal of College Student Development, 29(3), pp.196~209 (1988)
- Tinto, V., "Leaving College: Rethinking the Causes and Cures of Student Attrition" (1993), University of Chicago Press
- Youn, Bo Ra, "Temporal Aspects and Determinants of College Student Departure", Korean Journal of Sociology of Education, 25(1), pp.129~155 (2015)