Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Deep learning based teacher candidate acceptance prediction using college credits and activities

딥 러닝 기반 대학 이수학점 및 활동에 의한 교원임용 후보자 경쟁 시험 합격여부 예측

  • Kim, Geun-Ho (Department of Computer Education, Kongju National University) ;
  • Kim, Eui-Jeong (Department of Computer Education, Kongju National University)
  • Received : 2019.05.29
  • Accepted : 2019.06.20
  • Published : 2019.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The recent increase in preference for teacher jobs has led to a rise in preference for education colleges. Not all students can enter teachers, but they must pass the test called the competitive examination for teacher appointment candidates after graduation. However, due to the declining population, the and employment T.O.s are decreasing every year and the competition rate is rising steeply. Therefore, in order to concentrate on the recruitment exam upon entering the university, the university is becoming a huge academy for the exam, not a place to study and learn. We found a connection between students' overall school life and their use of study groups as well as their grades and whether they passed the competition test for teachers using deep running. The academic activities did not significantly affect the acceptance process, and the accuracy of the prediction of the acceptance rate was generally 70% accurate.

최근 교사 직업에 대한 선호도가 높아짐에 따라 사범대학 및 교육대학의 선호도가 높아지고 있다. 모든 학생들이 교사에 진출 할 수 있는 것이 아니라 졸업 후 교원임용 후보자 경쟁시험이라는 시험을 통과하여야한다. 그러나 인구수 감소에 따른 임용T.O는 매년 줄어들고 있고 경쟁률은 가파르게 오르고 있는 사정이다. 때문에 입학하면서 임용시험에 매진하고자 대학교가 학문을 연구하고 배우는 곳이 아닌 시험을 위한 거대한 학원이 되어가는 중이다. 이에 본 연구에서는 학점뿐이 아니라 학생들의 전반적인 학교생활 및 스터디그룹 활용 여부 등을 종합하여 딥 러닝을 이용한 교원임용 후보자 경쟁시험 합격여부의 연관성을 파악하였다. 합격에 대하여 학과활동 등이 크게 영향을 미치지는 않았고 합격률 예측에 대한 정확도는 대체적으로 70%의 정확성을 보였다.

Keywords

References

  1. G. H. Kim, C. I. Jeong, C. S. Kim, E. J. Kim, and C. S. Kang, "A Study on the Competitive Admission of Candidates for Teacher's Employment by Using Deep Learning," Conference on korea information and communication engineering, vol. 23, no. 1, pp.182-185, 2019.
  2. G. H. Kim, and E. J. Kim, "Design of a Hopeful Career Forecasting Program for the Career Education," International Journal of Information and Communication Engineering Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 8, pp.1055-1060, 2018.
  3. C. S. Kim, Big Data and Deep Learning practice practice, 1th ed., Seoul, : JoEunGlTer, 2019.
  4. Y. B. Yang, "A Study on Prediction of Parent School Satisfaction Using Educational Data Mining," Master. dissertation, Korea University, Seoul: DE, 2018.
  5. Y. J. Jung, S. M. Ahn, J. H. Yang, and J. J. Lee, "Comparison of Deep Learning Frameworks: About Theano, Tensorflow, and Cognitive Toolkit," Journal of Intelligence and Information Systems, vol. 23, no. 2, pp. 1-17, 2017. https://doi.org/10.13088/jiis.2017.23.2.001
  6. Y. H. Lee, and D. H. Koo, "A Study on Development Deep Learning Based Learning System for Enhancing the Data Analytical Thinking," Journal of The Korean Association of Information Education, vol. 21, no. 4, pp. 393-401, 2017. https://doi.org/10.14352/jkaie.2017.21.4.393
  7. J. H. Seo, "A Comparative Study on the Classification of the Imbalanced Intrusion Detection Dataset Based on Deep Learning," Journal of Korean Institute of Intelligent Systems, vol. 28, no. 2, pp. 152-159, Apr. 2018. https://doi.org/10.5391/JKIIS.2018.28.2.152