DOI QR코드

DOI QR Code

랜덤 포레스트를 활용한 만족도 사전조사에 따른 교육 역량 예측 분석

An Analysis of Educational Capacity Prediction according to Pre-survey of Satisfaction using Random Forest

  • 남기훈 (서경대학교 컴퓨터공학과)
  • Nam, Kihun (Dept. Computer Engineering, SeoKyeong Univ)
  • 투고 : 2022.10.31
  • 심사 : 2022.11.09
  • 발행 : 2022.11.30

초록

대학들은 급변하는 사회 환경에 적합한 교육역량 수준을 높이기 위해 다양한 방법들을 찾고 있다. 본 논문에서는 조사 항목을 수정, 보완한 만족도 사전조사를 개강 전에 실행하여 학업성취도를 높이고 전공 이탈자의 비율을 낮춰 교육 성과를 높이는 방안을 제안한다. 일반적인 만족도 조사 이후에 시행되는 교육품질 개선(CQI) 방식을 보완하고자 만족도 사전조사를 시행하였다. 학생역량을 강화하기 위해 설계가 진행 중인 인공지능형 메디치 플랫폼에 적용할 수 있는 머신러닝 기법의 랜덤 포레스트를 활용하여 중요한 데이터의 예측 및 분석을 가능하게 하였다. 만족도 사전조사 데이터들을 전처리하여 수강 신청 학생들의 정보를 설명 변수로 정의하고 분류하여 모델 생성 및 학습하였다. 실험 환경은 주피터 노트북 3.7.7, Python 3.7에서 관련 알고리즘과 사이킷런(sklearn) 라이브러리를 함께 사용하였다. 제안하는 방안의 결과를 수업에 반영하여 수업 후에 진행하는 교육 만족도 조사의 변화와 중도 탈락생 수의 동향을 비교 분석하였다.

Universities are looking for various methods to enhance educational competence level suitable for the rapidly changing social environment. This study suggests a method to promote academic and educational achievements by reducing drop-out rate from their majors through implementation of pre-survey of satisfaction that revised and complemented survey items. To supplement the CQI method implemented after a general satisfaction survey, a pre-survey of satisfaction was carried out. To consolidate students' competences, this study made prediction and analysis of data with more importance possible using the Random Forest of the machine learning technique that can be applied to AI Medici platform, whose design is underway. By pre-processing the pre-survey of satisfaction, the students information enrolled in classes were defined as an explanatory variable, and they were classified, and a model was created and learning was conducted. For the experimental environment, the algorithms and sklearn library related in Jupyter notebook 3.7.7, Python 3.7 were used together. This study carried out a comparative analysis of change in educational satisfaction survey, carried out after classes, and trends in the drop-out students by reflecting the results of the suggested method in the classes.

키워드

과제정보

This work was supported by Seokyeong University in 2021.

참고문헌

  1. Kim, Pil-Seong, "A Poetic Exploration on How to Enhance Various Capacities Based on "OECD Education 2030" in Higher Education", Journal of Character Education and Research, Vol. 4, No. 2, pp.1-14, 2019, DOI: 10.46227/JCER.4.2.1.
  2. https://it.donga.com/102288/
  3. Kim Sinae, "Qualitative Case Study on College Students's Experience of Academic Counseling: Focused on Experience with Different Grades", Journal of Learner-Centered Curriculum and Instruction, Vol. 20, No. 3, pp.549-577, 2020, DOI: 10.22251/jlcci.2020.20.3.549.
  4. Park Hyun-Jeong, Shin Junghwi, "Trend of Academic Resilience and Random Forest Analysis on Factors related to Academic Resilience in Korea", Asia Journal of Education, Vol. 23, No. 3, pp.501-527, 2022. https://doi.org/10.15753/aje.2022.9.23.3.501
  5. Jo So Young, Kyoo-Lak Cho, "A study on the needs of university education service and campus life adjustment for college freshmen", Journal of Learner-Centered Curriculum and Instruction, Vol. 19, No. 18, pp.1073-1097, 2019, DOI: 10.22251/jlcci.2019.19.18.1073.
  6. Cho, WonKee, Lee, Soojeong, "Relationship among College Admission System, College Students' College Life and Satisfaction on College Major, and their Academic Achievements", Journal of Learner-Centered Curriculum and Instruction, Vol. 16, No. 7, pp.673-700, 2016.
  7. Minjung Lee, Kim Soo Dong, "A study on the CQI System for the Quality Management of Competency-Base Education - Focusing on D University in Korea", Culture and Convergence, Vol. 41, No. 3, pp.35-48, 2019.
  8. Bo-Ram Cho, "A Study on CQI Form for Quality Management and Improvement of Class", Journal of Digital Convergence, Vol. 18, No. 5, pp.115-125, 2020, DOI: 10.14400/JDC.2020.18.5.115.
  9. Mitchell, T. M. "Evaluating Hypotheses", Machine Learning, 1997.
  10. Jin Eun Yoo, "Machine Learning for Largescale/Panel Data and Learning Analytics Data Analysis", Journal of Educational Technology, Vol. 35, No. 2, pp.313-338, 2019, DOI: 10.17232/KSET.35.2.313.
  11. Oh Miae, Choi Hyeonsu, Kim Suhyun, Chang Joonhyuk, Jin Jaehyeon, Cheon Mikyeong, "A Study on Social security Big Data Analysis and Prediction Model based on Machine Learning", Korea Institute for Health and Affairs, 2017.
  12. Yoon Eugene, "A Study on Status Analysis and the Development Strategies of University General Education for the 4th Industrial Revolution Era", Korea Journal of General Education, Vol. 14, No. 2, pp.311-325, 2020, DOI: 10.46392/kjks.2020.14.2.311.
  13. Park Joo-Ho, Ryu Kiung, "The Analyses of the Concepts, Contents, Satisfaction and Future Needs for College General Education", Korea Journal of General Education, Vol. 8, No. 2, pp.43-82, 2014.
  14. Shin Soyoung, Kwon Soungyoun, "A Study on the Development and Validity Verification of a Measurement Tool for Educational Satisfaction in University", Journal of Education Science, Vol. 12, pp.107-132, 2013.
  15. Alexandru Gegiuc, Markku Simila, Juha Karvonen, Mikko Lensu, Marko Makynen, Jouni Vainio, "Estimation of degree of sea ice ridging based on dual-polarized C-band SAR data" The Cryosphere, Vol. 12, pp.343-364, 2018, DOI: 10.5194/tc.12.343.2018