Journal of Science Education (과학교육연구지)

Science Education Research Institute Kyungpook National University (경북대학교 과학교육연구소)
권호 표지
DOI QR코드

DOI QR Code

Exploration of Factors on Pre-service Science Teachers' Major Satisfaction and Academic Satisfaction Using Machine Learning and Explainable AI SHAP

머신러닝과 설명가능한 인공지능 SHAP을 활용한 사범대 과학교육 전공생의 전공만족도 및 학업만족도 영향요인 탐색

  • Received : 2023.02.01
  • Accepted : 2023.04.22
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study explored the factors influencing major satisfaction and academic satisfaction of science education major students at the College of Education using machine learning models, random forest, gradient boosting model, and SHAP. Analysis results showed that the performance of the gradient boosting model was better than that of the random forest, but the difference was not large. Factors influencing major satisfaction include 'satisfaction with science teachers in high school corresponding to the subject of one's major', 'motivation for teaching job', and 'age'. Through the SHAP value, the influence of variables was identified, and the results were derived for the group as a whole and for individual analysis. The comprehensive and individual results could be complementary with each other. Based on the research results, implications for ways to support pre-service science teachers' major and academic satisfaction were proposed.

본 연구는 사범대 과학교육전공 재학생의 전공만족도와 학업만족도에 영향을 주는 요인을 머신러닝 모델인 랜덤 포레스트와 그래디언트 부스팅 모델과 SHAP 기법을 활용하여 탐색했다. 연구 결과, 그래디언트 부스팅 모델의 성능이 랜덤 포레스트보다 우수한 것으로 드러났으나 그 차이는 크지 않았다. 전공만족도에 영향을 주는 요인으로는 '본인 전공 교과에 해당하는 고교시절 과학교사 만족도', '교직 동기', '나이' 등이 있으며, 학업만족도는 '나이', '성별', '내신 과학 전문교과 이수여부'의 영향을 크게 받는 것으로 드러났다. SHAP value를 활용하여 변인의 영향력을 밝힐 수 있었고, 그 결과가 집단 전체에 대한 것과 개별적 분석으로 각각 도출이 가능했고, 서로 보완적 결과가 도출이 가능함을 확인하였다. 연구 결과를 바탕으로 과학교육과 재학생의 전공 및 학업 만족도를 지원하기 위한 방안을 제안하였다.

Keywords

References

  1. Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
  2. Chang, H. S., & Lee, H. J. (2011). Exploring Pre-service Science Teachers' Motivation for Career Choice and Their Self-Image as a Science Teacher. Journal of the Korean Association for Science Education, 31(1), 14-31.
  3. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Procedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
  4. Choi, J. H., & Lee, S. B. (2021). A longitudinal study of college students' academic achievement and department satisfaction according to the admissions process: Focusing on the case of D University. The Journal of Learner-Centered Curriculum and Instruction, 21(19), 75-90. https://doi.org/10.22251/jlcci.2021.21.19.75
  5. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.
  6. Han, E. S., & Kim, J. D. (2003). An Analysis of Influential Factors on College of Education Students' Academic Satisfaction. The Journal of Korean Teacher Education, 20(3), 313-335.
  7. Kang, S. B., & Kim, K. H. (2019). An Empirical Study on Adaptation to College and Learning Attitude of University Freshman's and the Different Effects of Admission System. The Korean Association of General Education, 13(6), 77-96.
  8. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
  9. Kim, H. S. (2009). An analysis of factors affecting procedure of entrance and career choice related to science in college of natural science and engineering. (Master's thesis). Hanyang University, Seoul, Korea.
  10. Kim, K. H., & Ha, H. S. (2000). A Study of Department Satisfaction Factors of Undergraduate Students. Korea Journal of Counseling, 1(1), 7-20.
  11. Kim, K. H., & Kang, S. B. (2016). Development and Validation of the College Life Adjustment Scale for University Freshmen. The Korean Association of General Education, 10(3), 253-293.
  12. Kim, S. Y. (2012). An Analysis of College Student Dropouts' Mobility Paths and Structure. Journal of educational studies, 43(3), 131-163.
  13. Lee, B. K., & Chang, S. C. (2008). The effect of educational backgrounds in high school sciences on the achievement of college sciences. The Journal of Curriculum Studies, 26(2), 191-210.
  14. Lee, B. W., & Kim, H. K. (2018). What Factors Affect Pre-service Teachers in Choosing Teaching Science as Career?: Teaching Motivations of Pre-Service Science Teachers in Korea. Journal of the Korean Association for Science Education, 38(2), 123-133.
  15. Lee, G. G., & Hong, H. G. (2022). The Effects of the Number, Ratio of Advanced Courses, and Variety in Science Elective Subjects on the Growth of High School Science Course Students' Attitude Towards Science. Journal of Science Education, 46(1), 80-92. https://doi.org/10.21796/JSE.2022.46.1.80
  16. Lee, G. Y., Choi, T. W., & Lee, Y. S. (2015). Stress Effects on employment of college students college life. Korean Review of Corporation Management, 6(2), 197-209. https://doi.org/10.20434/krmc.2015.08.6.2.197
  17. Lee, I., Kwak, Y. S., & Cho, H. S. (2019). A Survey Research on Science and Engineering College Students' Perception on Completing Prerequisite Science Courses in High School. Journal of Science Education, 43(2), 195-206.
  18. Lee, J. J., Lee, Y. R., Lim, D. H., & Ahn, H. C. (2021). A Study on the Employee Turnover Prediction using XGBoost and SHAP. The Journal of Information Systems, 30(4), 21-42.
  19. Lee, Y. G. (2020). Relationship between Department Satisfaction and Career Decision Efficacy in Pre-Service Teachers in a College of Education. The Journal of Educational Development, 40(2), 527-545. https://doi.org/10.34245/jed.40.2.527
  20. Li, C. (2016). A gentle introduction to gradient boosting. Retrieved from http://www.ccs.neu.edu/home/vip/teach/MLcourse/4_boosting/slides/gradient_boosting.pdf.
  21. Shim, H. J., & Lee, H. N. (2017). Influence of Pre-service Science Teachers' Selection of Earth Science I, II in High School and College Major on their Self-perceived Attitude and Academic Achievement in General Earth Science Lecture. Journal of the Korean Earth Science Society, 38(3), 239-249. https://doi.org/10.5467/JKESS.2017.38.3.239