• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.155-170
• /
• 2020

The purpose of this study was to apply machine learning techniques (Decision Tree, Random Forest, XGBoost) to data from the 4th~6th year of the Seoul Education Longitudinal Study to find the factors predicting the career maturity of middle school students in Seoul city. In order to evaluate the machine learning application result, the performance of the model according to the indicators was checked. In addition, the model was analyzed using the XGBoostExplainer package, and R and R Studio tools were used for this study. As a result, there was a slight difference in the ranking of variable importance by each model, but the rankings were high in 'Achievement goal awareness', 'Creativity', 'Self-concept', 'Relationship with parents and children', and 'Resilience'. In addition, using the XGBoostExplainer package, it was found that the factors that protect and deteriorate career maturity by panel and 'Achievement goal awareness' is the top priority factor for predicting career maturity. Based on the results of this study, it was suggested that a comparative study of machine learning and variable selection methods and a comparative study of each cohort of the Seoul Education Termination Study should be conducted.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.1
• /
• pp.53-61
• /
• 2020

In the information society, the ability of learners to use computers to conduct self-directed learning is important. Indeed, the higher the computer's ability to use computers, the more the academic achievement needs to be analyzed. The purpose of this study was to identify longitudinal trajectories of student awareness of ICT literacy and frequency of computer use. We also examined the effects of the longitudinal patterns on academic achievement and college major choice. A non-parametric approach, K-means for longitudinal data(KML) algorithm, was conducted using 9-year longitudinal data from Seoul Education Longitudinal Study (2010-2018). Findings indicated that a pattern presenting a higher awareness of ICT literacy and frequency of computer use showed better academic achievements and was likely to prefer to choose engineering-related majors.

• Journal of vocational education research
• /
• v.35 no.4
• /
• pp.89-107
• /
• 2016

The purpose of this study was to verify the causal relationship between self-directed learning ability and career maturity by Middle and High School Students in Seoul. This study used Seoul Education Longitudinal Study(SELS) data. Using autoregressive cross-lagged modeling, the results was followed. first, self-directed learning ability value was had a statistically significant positive effect in accordance with the time course from middle school 1st grade to high school 3rd grade. Second, career maturity also had a statistically significant positive effect in accordance with the time course from middle school 1st grade to high school 3rd grade. Third, previous self-directed learning ability had significant positive effect on the later career maturity, but the previous career maturity had no significant effect on later self-directed learning ability.

• Journal of The Korean Association of Information Education
• /
• v.23 no.6
• /
• pp.551-560
• /
• 2019

In the advanced information age, learning is an activity in which learners access information resources through computers and Internet to acquire and evaluate information on their own. The emergence of an online learning platform based on the fourth industrial revolution technology is developing into an environment in which elementary and secondary learners learn and study based on constructivism learning theory. In the online learning environment, the researches on the information retrieval ability of the elementary and secondary learners and the self-directed learning ability were found to be highly related. However, it is necessary to analyze the relation between information retrieval ability and self-directed learning ability through a cross-sectional study that is limited to specific curriculum and contents and expands the longitudinal research. In this study, the panel data of the Seoul Education Longitudinal Study collected over 8 years are used to find the difference in self-directed learning ability according to the longitudinal pattern of information retrieval ability and frequency.

• Communications of Mathematical Education
• /
• v.35 no.1
• /
• pp.97-118
• /
• 2021

Since the characteristics of teachers that affect mathematics academic achievement are constantly changing and affecting mathematics achievement, longitudinal studies that can predict and analyze growth are needed. This study used data from middle and high school students from 2013(first year of middle school) to 2017(second year of high school) of the Seoul Education Longitudibal Study(SELS). By classifying the longitudinal changes in mathematics academic achievement into similar subgroups, the direct influence of teachers' characteristics(professionalism, expectations, academic feedback) perceived by students on the longitudinal changes in mathematics academic achievement was examined. As a result of the study, it was found that the characteristics of mathematics teachers(professional performance, expectation, and academic feedback) in group 1(343 students), which included the top 14.5% of students, did not directly affect longitudinal changes in mathematics academic achievement. Students in the middle 2nd group(745, 32.2%) had academic feedback from the mathematics teacher, and the 2nd group(1225 students) in the lower 53%, which included most of the students, showed that the expectations of the mathematics teacher were the longitudinal mathematics achievement. The change has been shown to have a direct effect. This suggests that support for teaching and learning should also reflect this, as the direct influence of teachers' professionalism, expectations, and academic feedback on longitudinal changes in mathematics academic achievement is different according to the characteristics and dispositions of students.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.11-27
• /
• 2020

In this paper, we developed a big data platform to store, process, and analyze effectively on such education longitudinal study data. And it was applied to the Seoul Education Longitudinal Study(SELS) to confirm its usefulness. The developed platform consists of data preprocessing unit and data analysis unit. The data preprocessing unit 1) masking, 2) converts each item into a factor 3) normalizes / creates dummy variables 4) data derivation, and 5) data warehousing. The data analysis unit consists of OLAP and data mining(DM). In the multidimensional analysis, OLAP is performed after selecting a measure and designing a schema. The DM process involves variable selection, research model selection, data modification, parameter tuning, model training, model evaluation, and interpretation of the results. The data warehouse created through the preprocessing process on this platform can be shared by various researchers, and the continuous accumulation of data sets makes further analysis easier for subsequent researchers. In addition, policy-makers can access the SELS data warehouse directly and analyze it online through multi-dimensional analysis, enabling scientific decision making. To prove the usefulness of the developed platform, SELS data was built on the platform and OLAP and DM were performed by selecting the mathematics academic achievement as a measure, and various factors affecting the measurements were analyzed using DM techniques. This enabled us to quickly and effectively derive implications for data-based education policies.

• (The) Korean Journal of Educational Psychology
• /
• v.32 no.1
• /
• pp.99-130
• /
• 2018

The purpose of this study was to examine the longitudinal relationship between resilience and social support of school violence exposure types including school bullying, victimization, and dual experience. The study used data obtained from the third year (2012) of the Seoul Education Longitudinal Study of 1,137 elementary school students in grade 6 who reported experiencing school violence. The results of the autoregressive cross-lagged model are as follows. First, as a result of measuring the self-regression coefficients of resilience and social support of the youth exposed to school violence at 3 time points (2012, 2014, and 2016), it was found for all types of violence that resilience and social support at the previous time point showed a signigicant positive effect on the same variable at the next time point. Second, in the case of the cross-lagged effects of resilience and social support, the effect of previous social support on resilience at the next time point was statistically significant for the victimization group, but not for the bullying or dual experience groups. Third, considering the opposite path from resilience to social support, resilience at the previous time point had a significant influence on the social support at the next time point for both the bullying and victimization groups. This result is new and can be complementary to the cross-sectional studies so far using a longitudinal view. The results of this study suggest that the bullying and victimized students who are relatively more resilient are less likely to perceive social support than those who are not resilient. Finally, we discuss the longitudinal relationship between resilience and social support, the limitations of this study, and implications for future research.

• Education of Primary School Mathematics
• /
• v.24 no.1
• /
• pp.1-20
• /
• 2021

Factors influencing mathematics academic achievement are constantly changing and have direct and indirect effects on mathematics achievement, so longitudinal studies that can predict and analyze their growth are needed. This study uses longitudinal data on students from 2011 (5th grade of elementary school) to 2015 (2nd grade of middle school) of the Seoul Education Longitudinal Study, and divides them into groups with similar longitudinal changes in mathematics academic achievement. The direct and indirect effects of learning attitudes and achievement goals were examined. As a result of the study, it was found that learning effort and learning attitude had a direct effect on mathematics achievement in 1 group (2277 students, 67.7%), and learning attitude had a direct effect on mathematics achievement in 3 groups (958 students, 28.5%). And it was found that learning effort h ad an indirect effect. In addition, it was found that both learning attitudes, learning efforts, and achievement goals had no effect on the academic achievement of mathematics in the second group (127 students, 3.8%).

• The Journal of Korean Association of Computer Education
• /
• v.20 no.3
• /
• pp.35-46
• /
• 2017

The purpose of this study is to analyse the longitudinal relations between creativity, academic achievements, and utilization of computer & smartphone of middle school students. For this purpose, multivariate latent growth model was verified, using three year longitudinal panel data of Seoul Educational Longitudinal Study(2013-2015). Results indicated that the more students in their first year used computer & smartphone, the better scores they obtained on the creativity and academic achievements. As their grade goes up, while the growth rates of using computer & smartphone and creativity were related positively, the growth rates of using computer & smartphone and academic achievements -even though it was not statistically significant- were related negatively. In addition, the first year students, who obtained high level of scores on the creativity, obtained high level of scores on academic achievements, but this tendency was not significant as their grade goes up.

• The Mathematical Education
• /
• v.63 no.1
• /
• pp.19-33
• /
• 2024

This study investigates longitudinal patterns in middle school students' mathematics interest and achievement using panel data from the 4th to 6th year of the Gyeonggi Education Panel Study. Results from the multivariate growth mixture model confirmed the existence of heterogeneous characteristics in the longitudinal trajectory of students' mathematics interest and achievement. Students were classified into four latent classes: a low-level class with weak interest and achievement, a high-level class with strong interest and achievement, a middlelevel-increasing class where interest and achievement rise with grade, and a middle-level-decreasing class where interest and achievement decline with grade. Each class exhibited distinct patterns in the change of interest and achievement. Moreover, an examination of the correlation between intercepts and slopes in the multivariate growth mixture model reveals a positive association between interest and achievement with respect to their initial values and growth rates. We further explore predictive variables influencing latent class assignment. The results indicated that students' educational ambition and time spent on private education positively affect mathematics interest and achievement, and the influence of prior learning varies based on its intensity. The perceived instruction method significantly impacts latent class assignment: teacher-centered instruction increases the likelihood of belonging to higher-level classes, while learner-centered instruction increases the likelihood of belonging to lower-level classes. This study has significant implications as it presents a new method for analyzing the longitudinal patterns of students' characteristics in mathematics education through the application of the multivariate growth mixture model.