실천공학교육논문지 (Journal of Practical Engineering Education)

  • 제13권1호
  • /
  • Pages.125-139
  • /
  • 2021
  • /
  • 2288-405X(pISSN)
  • /
  • 2288-4068(eISSN)
한국실천공학교육학회 (Korean Institute for Pratical Engineering Education)
권호 표지
DOI QR코드

DOI QR Code

온라인평생교육원의 STEP 온라인 수강생들의 특성 분석

Analysis of Online Students' Characteristics at STEP of Online-Lifelong Education Institute

  • 문철한 (한국기술교육대학교 컴퓨터공학부) ;
  • 최성준 (한국기술교육대학교 컴퓨터공학부) ;
  • 김미화 (한국기술교육대학교 HRD학과) ;
  • 명재규 (한국기술교육대학교 강소기업경영학과) ;
  • 민준기 (한국기술교육대학교 컴퓨터공학부)
  • Moon, Cheolhan (School of Computer Science and Engineering, Korea University of Technology and Education) ;
  • Choe, Seong Jun (School of Computer Science and Engineering, Korea University of Technology and Education) ;
  • Kim, Mi Hwa (Department of HRD, Korea University of Technology and Education) ;
  • Myung, Jae Kyu (Department of Small and Medium Enterprise Management, Korea University of Technology and Education) ;
  • Min, Jun-Ki (School of Computer Science and Engineering, Korea University of Technology and Education)
  • 투고 : 2021.03.30
  • 심사 : 2021.04.17
  • 발행 : 2021.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 온라인평생교육원에서 제공하는 STEP의 온라인 서비스 수강생 15.7만여 명 및 51만여 건의 수강 데이터를 대상으로 기술 통계적 분석을 수행했다. STEP의 교육과정 유형인 기업맞춤, 상시제, 기수제에 따라서 각 유형별 수강생의 성적 분포를 분석하여, 그 성적의 분포가 10점 미만과 90점 이상이 다수인 극단적인 분포임을 확인하였다. 추가적으로, 미수료 수강생의 데이터를 대상으로 한K-평균 군집화를 수행하여 미수료 수강생들의 특성을 분석하였다. 그 결과, 30-40대, 여름에 수강한 수강생들의 미수료율이 높다고 확인하였다. 또한, 전체 수강생들의 수료 여부 정보에 대하여 의사결정나무 기법을 적용하여 분석한 결과 다수의 강좌를 수강하는 남성, 전문대졸 수강생들의 미수료율이 높다는 것을 알 수 있었다. 따라서, STEP 수강생들의 수료율을 높이기 위해 이러한 수강생들을 대상으로 학습을 더 독려할 필요가 있다.

In this paper, we conducted a descriptive statistical analysis on the data of about 157 thousands of students and 510,000 enroll data of the STEP online service provided by the Online Lifelong Education Institute. According to the classification such as company adaptation, regular and cardinal, we analyzed the distributions of students' grades for each classifications. As the result of analyzation, it was shown that the distribution of grades is extreme skewed such that there are large numbers of less than 10 points or more than 90 points. In addition, K-means clustering was performed on the data of uncompleted students to analyze the characteristics of them. As a result, it was confirmed that the non-completion rate of students in 30 s and 40 s ages who took the course in the summer, was high. Furthermore, as a result of applying the decision tree technique to the completion status information of all students, we found that the uncompleted rate of male and vocational college graduates taking a large number of courses was high. Consequently, we have to encourage learning to such STEP students in order to increase the completion rate.

키워드

과제정보

본 논문은 한국기술교육대학교 온라인 평생교육원의 지원을 받아 연구되었음.

참고문헌

  1. Korean Educational Development Institute, "2020-07 Domestic e-learning demand and introduction of regular educational institutions," July 27, 2020 [Online]. Available: https://kess.kedi.re.kr/mobile/post/6703968?itemCode=03&menuId=m_02_03_02.
  2. National Institute for Lifelong Education, "Korean Massive Open Online Course(K-MOOC)," [Online]. Available: http://www.kmooc.kr/
  3. Online Lifelong Education Institute, "Smart Training Education Platform (STEP)," [Online]. Available: https://www.step.or.kr/main.do.
  4. S. H. Im, Y. G. Lee, and S. Y. Lee, "A comparative study on the predictive model of career identity of middle school and high school seniors using decision tree analysis method," Korean Journal of Youth Studies, vol. 27, no. 6, pp. 337-365, June 2020 https://doi.org/10.21509/KJYS.2020.06.27.6.337
  5. J. Y. Han and S. H. Lee, "Investigating online learning types based on self-regulated learning in online software education," The Journal of Korean Association of Computer Education, vol. 22, no. 5, pp. 51-65, September 2019.
  6. A. Jindal, A. Dua, K. Kaur, M.Singh, N. Kumar, and S. Mishra, "Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid," IEEE Transactions on Industrial Informatics, vol. 12, no. 3, pp. 1005-1016, June 2016. https://doi.org/10.1109/TII.2016.2543145
  7. C. Yuan and H. Yang, "Research on K-value selection method of K-means clustering algorithm," J-Multidisciplinary Scientific Journal, vol. 2, no. 2, pp. 226-235, June 2019. https://doi.org/10.3390/j2020016
  8. C. M. Bishop, Pattern Recognition and Machine Learning, 1st ed. Springer: New York, 2016.
  9. H. B. Bang, "A structural analysis of factors affecting adult learners learning outcomes at the university lifelong educational institutions," Journal of the Korea Academia-Industrial cooperation Society, vol. 16, no. 11, pp. 7474-7484, November 2015. https://doi.org/10.5762/KAIS.2015.16.11.7474
  10. H. D. Lee, "Clustering university e-learning learners in the perspective of learning analytics and analyzing the differences in academic achievement among clusters," Journal of Lifelong Learning Society, vol. 14. no. 3, pp. 97-118, October 2018. https://doi.org/10.26857/jlls.2018.8.14.3.97
  11. I. S. Lee, J. H. Leem, E. M. Sung, and S. H. Jin, "A study on the development of collaborative learning model and behavioral elements in e-learning environment," The Journal of Korean Association of Computer Education, vol. 9, no. 2, pp. 27-36, March 2006.
  12. H. R. Moon and H. S. Lee, "The correlation between learning motives and completion rate in K-MOOC online courses : focusing on classes in the animation field," The Korean Journal of Animation, vol. 15, no. 4, pp. 210-228, December 2019. https://doi.org/10.51467/ASKO.2019.12.15.4.210
  13. M. J. Oh, "The effect of self-regulation learning, teaching presence, and academic achievement in the K-MOOC setting," Journal of Lifelong Learning Society, vol. 16, no. 2, pp. 191-212, May 2020. https://doi.org/10.26857/JLLS.2020.5.16.2.191
  14. C. H. Ahn, S. K. Joung, S. W. Kim, and I. H. Choi, "The analysis of e-learning learners characteristics for improving teaching and learning in online," Journal of Korean Institute of Information Technology, vol. 14, no. 4, pp. 187-194, April 2016. https://doi.org/10.14801/jkiit.2016.14.4.187
  15. I. Ben-Gal, "Outlier Detection" in Data Mining and Knowledge Discovery Handbook, 1st ed., O. Maimon, and L. Rokach, (eds), Springer, Boston, MA, 2005.
  16. R. Lleti, M. C. Ortiz, L. A. Sarabia, and M. S. Sanchez, "Selecting variables for k-means cluster analysis by using a genetic algorithm that optimises the silhouettes," Analytica Chimica Acta, vol. 515, no. 1, pp. 87-100, July 2004. https://doi.org/10.1016/j.aca.2003.12.020