• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1255-1262
• /
• 2021

The proportion of students dropping out of universities is increasing year by year, and they are trying to identify risk factors and eliminate them in advance to prevent dropouts. However, there is a problem in the management of students at risk of dropping out and the forecast is inaccurate because crisis students are managed through the univariable analysis of specific risk factors. In this paper, we identify risk factors for university dropout and analyze multivariables through machine learning method to predict university dropout. In addition, we derive the optimization method by evaluation performance for various prediction methods and evaluate the correlation and contribution between risk factors that cause university dropout.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.373-385
• /
• 2021

In this study, the Korea Youth Policy Institute applied a self-registering model to verify the patterns of parental stress, multicultural youth psychological maladjustment, and interdependence between three factors by using five-point-time data tracked from middle school to high school. According to the analysis, First, Parent' stress at the time of the five surveys had a significant positive effect on the psychological maladjustment and the risk of academic interruption of multicultural adolescents at that point. Second, the psychological maladaptation of multicultural adolescents at the time of the previous five surveys had a significant positive effect on the risk of academic interruption at that point. Based on these analysis results, various support measures were proposed to cope with the stress of multicultural youth parents, and policy alternatives were proposed to prevent the risk of academic interruption by reducing the psychological maladjustment of multicultural youth.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.6584-6594
• /
• 2015

This study is intended to come up with the Scale of the danger in the adolescents' school-dropout. The present dissertation developed the questions and collected them on the base of the potential variables, that consist of the school-dropout of adolescents, and the operational definition of each variable, through the verification of the precedent research and the review of the related literatures. In addition, the interviews for the teachers who have experienced the school-dropouts of adolescents are performed and are analyzed, and then the relevant questions were culled. The Scale developed in this study is composed of 48 questions and 10 factors. The questions which have the same factors and clustered are reflected, and then are discerned into 3 dimensions, that is, the outer attitude, the inner attitude, and the attitude of parents. The Scale of the danger in the adolescents' school-dropout which is contrived through this study is expected to prevent school-dropouts to teenagers and the teachers.

• The Journal of the Korea Contents Association
• /
• v.15 no.4
• /
• pp.277-290
• /
• 2015

The main purpose of study is to identify relevance between nature and types of risk factors that delinquent teenagers are exposed and types of methodologies implemented to prevent committing school violence, domestic violence, and suicide or to help recovering from violent activities and suicide attempts. The results show that school dropout has much relevance in risk factors such as probation, lawbreaking, smoking, drinking, runaway, domestic violence victim, and suicidal attempt. Risk rate of school dropout for those teenagers who smoke and drink in the period of runaway is 2.76 times higher than those teenagers who do not smoke or drink. More specifically, drinking increases more risk of school dropout than smoking. Contribution of this study is to identify empirical evidence that calls for comprehensive risk management for delinquent teenagers encompassing home, school, and community rather than focusing on risk itself.

• Korean Journal of Social Welfare
• /
• v.68 no.3
• /
• pp.105-125
• /
• 2016

School absenteeism is considered one of the early predictors of school drop-out and serious delinquency or criminal behavior. The primary goal of the current study was to explore the protective and risk factors related to changing school absenteeism over time based on the ecological-systemic perspective. The data was derived from the Korean Children and Youth Panel Survey (KCYPS) using the 2011 and 2012 survey waves collected from 2,378 elementary school students. Using this data, Panel Fixed Effects Analysis was conducted. Major findings indicated that daily computer usage, parental abuse, school activity attendance, and school grades had an effect on students missing school days over time. Specifically, high levels of computer usage and parental abuse were related to increased school absenteeism, while high levels of school activity attendance and school grades were associated with decreased school absenteeism. These findings emphasized the importance of predictive intervention for children and suggested the need to construct a school absenteeism monitoring system in South Korea.

• Korean Journal of School Psychology
• /
• v.18 no.1
• /
• pp.31-48
• /
• 2021

The purpose of this study was to determine whether the retention of university freshmen could be predicted using their peer relationships in a specific department. In this study, retention was defined as a student staying enrolled in their university for a certain period of time. Social relationships are formed through interaction between people, so both students' self-perceptions and others' perceptions of them must be accounted for, so we used a social network analysis that did so. We examined social networks visualizations that allowed for a rich interpretation of numerical information. Participants in this study were freshmen who enrolled in an undergraduate program in 2017, 2018, or 2019. We used the name generator method to determine how quantitative friendship network variables predicted the academic retention up to the first semester of 2020. Cox proportional hazard model analysis showed that the weighted indegree centrality with intimacy positively predicted retention. The results of this study can be used to identify and conduct interventions for students who may be likely to disenroll. However all of the students did not participate in the department, it was difficult to examine their entire peer networks. Thus, this study's results cannot be generalized because the participants are students of a specific major, so further research is needed to produce more generalizable results.

• Korean Journal of Social Welfare Studies
• /
• no.39
• /
• pp.5-28
• /
• 2008

The purpose of this study is two-fold: 1) to identify different adolescent smoking trajectories in Korea; and 2) to examine predictors of those smoking trajectories within a social developmental frame. Data were from the Korea Youth Panel Survey(KYPS), a longitudinal study of 3,449 youths followed since 2003. Using semi-parametric group-based modeling, four smoking trajectories were identified: non initiators, late onsetters, experimenters, and escalators. Multinomial logistic regressions were then used to identify risk and protective factors that distinguish the trajectory groups from one another. Among non smokers at age 13, late onsetters were distinguished from non initiators by a variety of factors in every ecological domain. Among youths who already smoked at age 13, escalators who increased their smoking were distinguished from experimenters who almost desisted from smoking by age 17 by self-esteem and academic achievement. Finally, implications for youth welfare practice from this study were discussed.