• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.979-987
• /
• 2013

It is becoming increasingly difficult for colleges to recruit new students to their full capacity. The increase of the withdrawal rate drives these colleges into crisis yet little has been done about it, because students with great possibility to withdraw enter colleges and old measures to stop them from dropping out hardly work. This study attempts to grope new measures to prevent dropout from college. To do this, I investigated withdrawal rate by college admission types and suggested measures to reduce withdrawal rate by incorporating the results of the investigation into admission procedures. I also compared the different types of admission in students satisfaction with college life and withdrawal rate, and suggested the measures to alleviated withdrawal rate. I expect the suggestions made in this study would be used effectively to reduce the withdrawal in colleges.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.175-183
• /
• 2019

Drop-out issue is one of the challenges of cyber university. There are about 130,000 students enrolled in cyber universities, but the dropout rate is also very high. To lower the dropout rate, cyber universities invest heavily in learning analytics. Some cyber universities analyze the possibility of dropout and actively support students who are more likely to drop out. The purpose of this paper is to identify the learning data affecting the dropout prediction index. As a result of the analysis, it is confirmed that number of lessons(progress), credits, achievement and leave of absence have a significant effect on dropout rate. It is necessary to increase the accuracy of the prediction model through post-test on the student dropout prediction index.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.149-153
• /
• 2011

이 연구는 전자교육에서 성인여성 학습자를 중도탈락에 이르게 하는 요인을 도출하고, 이 중에서 가장 큰 영향을 주는 요인을 찾음으로써, 궁극적으로는 수료율을 제고하는데 목적이 있다. 이를 위해, 선행연구 분석을 통해 도출된 9가지 요인 중 어떤 요인이 중도탈락에 영향을 미치고, 그 영향력은 얼마인지 알아보기 위해 16개의 설문문항을 구성하여 K 기관의 교육생을 대상으로 설문을 실시하였다. 연구결과, 전자교육에서 성인여성 학습자의 중도탈락에 영향을 주는 요인은 결혼 여부, 내적 동기, 교육기관의 지원, 가사와 육아, 학습가능 시간 등 5가지로, 내적 동기, 학습가능 시간, 결혼 여부, 교육기관의 지원, 가사와 육아 순으로 중도탈락에 대한 영향을 미쳤다. 즉, 학습진행 시 내적 동기의 만족도가 높을수록, 학습 시간의 부담이 적을수록, 미혼이며, 교육기관의 지원에 만족도가 높을수록, 또 가사와 육아에 부담이 적을수록 수료를 할 가능성이 더 큰 것으로 나타났다. 연구결과를 토대로 전자교육에서 성인여성 학습자의 수료율을 제고하기 위해서는 성인여성을 대상으로 한 전자교육 과정 운영 시 결혼 여부, 내적 동기, 교육기관의 지원, 가사와 육아, 학습가능 시간의 요인을 고려해야하며, 그 중 결혼 여부, 가사와 육아부담 등의 여성학습자의 일반적인 특성에 따른 중도탈락을 줄이기 위해서는 교육기관의 역할이 중요하다. 또한, 성인여성 학습자의 중도탈락에 가장 큰 영향을 미치는 내적 동기 향상을 위해 과정설계 시 여성학습자 위주의 맞춤형 교수설계전략을 세우는 것이 중요하다. 성인여성 대상 전자교육에서의 학습자 중도탈락 요인들의 인과관계 및 그에 따른 영향력을 분석하는 연구를 통해 도출된 결과를 바탕으로 성인여성 학습자의 중도탈락을 줄일 수 있는 실증적인 방법론에 대한 연구를 통해 중도탈락률을 줄이는 것은 물론, 학업성취도 및 만족도를 높이고 나아가서는 여성의 사회진출을 도울 수 있는 연구가 필요하다.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.1
• /
• pp.1-12
• /
• 2014

Since students' behaviors during e-learning are automatically stored in LMS(Learning Management System), the LMS log data convey the valuable information of students' engagement. The purpose of this study is to develop a prediction model of e-learning course dropout by utilizing LMS log data. Log data of 578 college students who registered e-learning courses in a traditional university were used for the logistic regression analysis. The results showed that attendance and study time were significant to predict dropout, and the model classified between dropouts and completers of e-learning courses with 96% accuracy. Furthermore, the feasibility of early detection of dropouts by utilizing the model were discussed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.169-171
• /
• 2013

본 연구는 초등학생을 대상으로 전자교육 학습자의 학습이력에 따른 중도탈락 원인들을 규명하고 재수강 의사 결정에 차이를 보이는지 분석을 통해 학습자의 재수강을 높일 수 있는 방안을 검토하고 효율적인 전자교육 프로그램을 운영할 수 있도록 시사점을 제공하기 위한 것이다. 구체적으로는 초등 전자교육에서 학습이력별 중도탈락 원인을 규명하고 재수강 의사 결정에 차이가 있는지 분석하였다. 연구결과 첫째, 초등전자교육에서 학습자의 학습이력 중 특히 학습자의 이수율이 중도탈락율과 관련 있으며, 유의한 원인은 시간부족, 교육내용 방법 평가로 나타났다. 둘째, 시간이 부족하거나 교육내용 방법 평가 방법이 적절하지 않아 중도탈락한 학습자들의 50% 이상이 재수강 의사를 밝혔으며, 중도탈락 원인 중 학업능력은 재수강을 결정하는데 유의한 원인으로 파악되었다. 셋째, 중도 탈락자의 재수강을 유도하는 방안으로서는 초등 전자교육 수강자는 온라인 플래너를 활용하여 매일 1시간씩 학습 시간을 관리하는 것이 필요하며, 선행학습은 한 학기 전까지 다루는 것이 좋은 것으로 나타났다.

• Journal of The Korean Association of Information Education
• /
• v.11 no.2
• /
• pp.205-218
• /
• 2007

This study investigates the reasons of dropout in a survey of 348 dropouts from a cyber university located in Seoul, Korea. Most common reasons are time constraints due to work or family-related needs. Difficulties in adjusting to online learning environment and uncertainties regarding the value of a cyber university degree also played important roles. Drop-out students who pointed to these two reasons also suffered from lack of communication and interaction with other students and professors. Efforts to address these issues are in order as well as the development of time-efficient learning strategies and financial aids.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.404-412
• /
• 2010

The purpose of this study is to suggest the basic data for lowering cyber university students' dropout rate and fostering continuous learning environment through understanding that cyber university student's private variance, an education institute variance and social variance have the impact on a student's determining dropout. For this, we selected students in A cyber university and carried out surveys for 500 students from April first to May 31st, 2009 using convenience sampling. We excluded answers whose results are considered to be insufficient or overlapped among answers of 336 students and used 304 answers in this study. We carried out logistics regression analysis using SPSS for Winow 15.0 for data analysis. First, it proved that individual interest variance affects the dropout. Second, it turned out that educational institute's environment variance has impact on the dropout. Third, it proved that social environment factor affects the dropout. Fourth, only individual variance among individual, an educational institute and social variance has meaningful impact on the dropout in terms of statistics.

• Korean Journal of Social Welfare
• /
• v.60 no.3
• /
• pp.231-251
• /
• 2008

The purpose of this study was to determine the factors affecting the drop-out from the domestic violence offenders' treatment group programs in Korea, on the assumption that it would be an important challenge to prevent the domestic violence offenders from dropping out from their treatment group programs in order to protect the victim women and improve effectiveness of the programs. For this purpose, the researchers sampled a total of 280 domestic violence offenders who had participated in the domestic violence offenders' treatment programs operated by 65 domestic violence counselling organizations throughout the nation. As a result, it was found that 159(56.8%) out of the 280 offenders had completed the programs, while 121(43.2%) had dropped out from the programs. As a consequence of comparing the two groups, it was disclosed that they differed significantly in terms of cohabitation with spouse and attitude toward sex role. As a result of the logistic regression analysis for the factors affecting the drop outs from the treatment group program, it was found the significant factors were employment, path of being referred to the program and attitude toward sex role.

• Journal of the Korea society of information convergence
• /
• v.1 no.1
• /
• pp.47-54
• /
• 2008

This study analyzed the status and causes for the dropouts of college based on the survey conducted among 14,210 freshmen attending D College, other than the supernumerary special selection, from 2001 through 2005. A significant difference was shown in all items of general characteristics. The dropout rate of women, generally selected and general highschool graduated were higher than for men, specially selected and special high school graduated, respectively. The most dropouts were due to Not Return(40.16%), followed by Unenrolled(32.98%), Voluntary Leave(26.05%) and Expelled(0.81%) in order. In the distribution of the central tendency values measured from the entire subjects, the high school records and the days of absence showed a positive skewness, while the college records showed a negative skewness with the data mostly around a higher grade. The standard deviation indicating that the dropouts got the scores higher than those of the continuing students demonstrated that there was relatively insignificant difference in scores between two groups. It was demonstrated that both the high school records and the days of absence affected the dropout. The lower the high school records were, and the more the days of absence were, the more influence both items had on the dropout. The influence degree of each item was similar. Lower the scores were in terms other than the first term in the freshmen year, the more influence it had on the dropout. The most dropouts were influenced by the scores of the freshmen year, followed by the credits of the second term, the scores of the first term, the scores of the second term, and the credits of the first term in the freshmen year. Among the general characteristic items, the most dropouts were influenced by the course of study, followed by the gender. The effect of other items was insignificant.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.1-15
• /
• 2019

One of the biggest difficulties in the vocational training field is the dropout problem. A large number of students drop out during the training process, which hampers the waste of the state budget and the improvement of the youth employment rate. Previous studies have mainly analyzed the cause of dropouts. The purpose of this study is to propose a machine learning based model that predicts dropout in advance by using various information of learners. In particular, this study aimed to improve the accuracy of the prediction model by taking into consideration not only structured data but also unstructured data. Analysis of unstructured data was performed using Word2vec and Convolutional Neural Network(CNN), which are the most popular text analysis technologies. We could find that application of the proposed model to the actual data of a domestic vocational training institute improved the prediction accuracy by up to 20%. In addition, the support vector machine-based prediction model using both structured and unstructured data showed high prediction accuracy of the latter half of 90%.