정보교육학회논문지 (Journal of The Korean Association of Information Education)

  • 제25권5호
  • /
  • Pages.813-824
  • /
  • 2021
  • /
  • 1229-3245(pISSN)
  • /
  • 2733-8428(eISSN)
한국정보교육학회 (Korea Association of Information Education)
권호 표지
DOI QR코드

DOI QR Code

성인 학습자의 학습 추이 분석을 위한 인공지능 기반 알고리즘 모델 개발 및 평가

Development and evaluation of AI-based algorithm models for analysis of learning trends in adult learners

  • 정영식 (전주교육대학교 컴퓨터교육과) ;
  • 이은주 (한국교육개발원 디지털교육연구센터) ;
  • 도재우 (한국교육개발원 디지털교육연구센터)
  • Jeong, Youngsik (Department of Computer Education, Jeonju National University of Education) ;
  • Lee, Eunjoo (Korean Educational Development Institute) ;
  • Do, Jaewoo (Korean Educational Development Institute)
  • 투고 : 2021.06.23
  • 심사 : 2021.09.09
  • 발행 : 2021.10.29
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A사이버교육시스템 성인학습자의 자기조절학습 관련 학습 추이를 분석하여 교육 성과를 높이기 위해 인공지능을 활용한 알고리즘 모델을 다양하게 설계하고, 그것을 실제 데이터에 적용함으로써 성능을 평가하였다. 이를 위해 A사이버교육시스템에서 115명의 성인학습자의 로그 데이터를 분석하였다. A사이버교육시스템 성인학습자들은 대부분 권장 학습 시간 이상을 학습하였으나, 학기 말에는 권장 학습 시간 대비 실제 학습 시간이 현저하게 감소하였다. VOD 참여율이나 형성평가 참여율, 학습 활동 참여율에서도 학습 후반부에 접어들수록 학습 참여율이 떨어졌다. 따라서 교육 성과를 높이려면 학습 시간이 후반에도 지속될 수 있도록 지원해야 한다 판단하여 후반부에 학습 시간이 떨어지는 학습자를 찾아내기 위해 Tensorflow를 활용한 인공지능 모델을 개발하여 수강 시작 날짜별 학습 시간을 예측하였다. 그 결과, CNN 모델을 활용하여 단일 출력 또는 다중 출력을 예측할 경우 다른 모델에 비해 평균 절대 오차가 가장 낮게 나타났다.

To improve educational performance by analyzing the learning trends of adult learners of Open High Schools, various algorithm models using artificial intelligence were designed and performance was evaluated by applying them to real data. We analyzed Log data of 115 adult learners in the cyber education system of Open High Schools. Most adult learners of Open High Schools learned more than recommended learning time, but at the end of the semester, the actual learning time was significantly reduced compared to the recommended learning time. In the second half of learning, the participation rate of VODs, formation assessments, and learning activities also decreased. Therefore, in order to improve educational performance, learning time should be supported to continue in the second half. In the latter half, we developed an artificial intelligence algorithm models using Tensorflow to predict learning time by data they started taking the course. As a result, when using CNN(Convolutional Neural Network) model to predict single or multiple outputs, the mean-absolute-error is lowest compared to other models.

키워드

과제정보

본 논문은 한국교육개발원(2020)의 '방송중·고 맞춤형 교육지원을 위한 학습 분석 모형 개발 연구' 지원비로 연구되었음.

참고문헌

  1. Choi, J. Y. (2012). Trend of Big Data in Smart Education Environment. Korea Education and Research Information Services.
  2. de Barba, P. G., Malekian, D., Oliveira, E. A., Bailey, J., Ryan, T., & Kennedy, G. (2020). The importance and meaning of session behaviour in a MOOC. Computers & Education, 146, 103772. https://doi.org/10.1016/j.compedu.2019.103772
  3. Gadella, L. U., Estevez-Ayres, I., Fisteus, J. A., & Delgado-Kloos, C. (2020, April). Application of learning analytics to study the accuracy of self-reported working patterns in self-regulated learning questionnaires. In 2020 IEEE Global Engineering Education Conference (EDUCON) (pp. 1201-1205). IEEE.
  4. Gruver, N., Malik, A., Capoor, B., Piech, C., Stevens, M., & Paepcke, A. (2019). Using latent variable models to observe academic pathways. arXiv preprint arXiv:1905.13383.
  5. Han. S. H. (2007). The Relationship between Academic Motivation and Self-Directed Leaning among Adult Learners. The Journal of Learner-Centered Curriculum and Instruction 7(2), 355-374.
  6. Hong, S.. Cho, B., Choi, I., Park, K., Kim, H., Park, Y., & Park, J. (2020). Artificial Intelligence and EduTech in School Education. Korea Institute for Curriculum and Evaluation.
  7. Jeong, Y. S., Lee, E. J., Do, J. W., & Jung, J. W. (2021). Learning status analysis of the Open High School using artificial intelligence, Journal of The Korean Association of Information Education, 12(1), 117-122.
  8. Jo, I. H., Ha, K. H., Park & Y. J. (2015). Measuring Information Perception in Learning Analytics Dashboard: Use of Eye-Tracking System. Journal of Korean Association for Educational Information and Media, 21(3), 441-469. https://doi.org/10.15833/KAFEIAM.21.3.441
  9. Jo, I. H., Kim, J. H., & Kang, Y. J. (2012). Investigation of Statistically Significant Period for Achievement Prediction Model in e-Learning. Journal of Educational Technology, 29(2), 285-306.
  10. Joeng, K. H., Kim, S. M., Kim, S. A., Son, C. H., Lee, S. C., Lee, E. C., & Jo, D. J. (2017). A study on the design method of digital learning contents for Open Secondary Schools applying the 2015 revised curriculum. Korean Educational Development Institute.
  11. Kang, M. S., Kim, J. I., & Park, I. W. (2009). The Examination of the Variables related to the Students' e-learning Participation that Have an Effect on Learning Achievement in e-learning Environment of Cyber University. Journal of Korean Society for Internet Information, 10(5), 135-143.
  12. Kim, H. J., Lee, S. J., & Kim, J. I. (2011). The study on influential factors upon learning achievement and its reuse of e-learning in university. The Journal of Internet Electronic Commerce Research, 11(1), 201-228. https://doi.org/10.1007/s10660-010-9072-y
  13. Kim, K. J., & Han, H. J. (2021). A Design and Effect of Maker Education Using Educational Artificial Intelligence Tools in Elementary Online Environment. Journal of Digital Convergence, 19(6), 61-71. https://doi.org/10.14400/JDC.2021.19.6.061
  14. Kim, S. B., & Lim, K. Y. (2017). The moderating effects of perceived usefulness and self-regulated learning skills on the relationship between participative motivation and learning satisfaction in online continuing education programs. Journal of Lifelong Learning Society, 13(3), 85-107. https://doi.org/10.26857/JLLS.2017.08.13.3.85
  15. Korean Educational Development Institute. (2020a). 2020 Open High School : Where your dream of learning becomes a reality.
  16. Korean Educational Development Institute (2020b). The current status of Open High Schools for the first semester of 2020.
  17. Kown, S. Y. (2009). The Analysis of differences of learners participation, procrastination, learning time and achievement by adult learners adherence of learning time schedule in e-Learning environments. The Journal of Learner-Centered Curriculum and Instruction, 9(3), 61-86.
  18. Lee, E. J., Son, C. H., Kim, S. M., Kim, S. J., Ryu, J. H., Kim, J. H. Ahn, S. H., & Kim J. S. (2019). A study on the establishment and operation standards for Open Secondary Schools. Korean Educational Development Institute.
  19. Lee, E. J., Do, J. W.,Yoo, M. N., Jung, J. W., & Lee, J. Y. (2021). Learning Analytics Model to Support Self-regulated Learning in Open Secondary School. Journal of Korean Association for Educational Information and Media, 27(1), 223-251. https://doi.org/10.15833/KAFEIAM.27.1.223
  20. Lee, J. Y. (2019). Exploring the Learning Experience of Adult Learners at Cyber Universities, Korean Journal of Social Quality, 3(1), pp. 61-78. https://doi.org/10.29398/kjsq.2019.3.1.61
  21. Lee, K. N., & Choi, W. S. (2007). A study on the self-regulated learning factors affecting participation, satisfaction in e-learning. The Korean Journal of Technology Education, 7(3), 211-224.
  22. Lee, J. S., Moon, K. B., Han, S. Y., Lee, S. K., Kwon, H. J., Han, J. H., & Kim, G. T. (2021). Development and Application of an AI-Powered Adaptive Course Recommender System in Higher Education: An Example from K University. Journal of Educational Technology, 37(2). 267-307. https://doi.org/10.17232/KSET.37.2.267
  23. Lim, M. I., Kim, H. M., Nam, J. H., & Hong, O. S. (2021). Exploring the Application of Elementary Mathematics Supporting System using Artificial Intelligence in Teaching and Learning. Journal of Korea Society Educational Studies in Mathematics School Mathematics, 23(2), 251-270.
  24. McMahon, M., & Oliver, R. (2001). Promoting self-regulated learning in an on-line environment. Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications. Chesapeake, VA.
  25. Park, H. J., & Choi, M. S. (2008). Relationships between e-learning effectiveness and its related factors in higher education. Journal of Educational Technology, 24(1), 27-53. https://doi.org/10.17232/KSET.24.1.27
  26. Papamitsiou, Z., & Economides, A. A. (2019). Exploring autonomous learning capacity from a self-regulated learning perspective using learning analytics. British Journal of Educational Technology, 50(6), 3138-3155. https://doi.org/10.1111/bjet.12747
  27. Pintrich, P.R., & Zusho, A. (2002). The development of academic self-regulation: The role of cognitive and motivational factors. In A. Wigfield, & J.S. Eccles(Eds.), Development of achievement motivation (pp. 249-284). San Diego, CA: Academic.
  28. Kwon, S. (2009). Impact of Learner's Time Management Strategies on Achievement in an e-learning Environment: A Learning Analytics Approach. Impact of Learner's Time Management Strategies on Achievement in an e-learning Environment: A Learning Analytics Approach, 9, 61-86.
  29. Sung, E. M., Jin, S. H., & Yu, M. (2016). Exploring learning data for supporting self-directed learning in the perspective of learning analytics. Journal of Educational Technology, 32(3), 487-533. https://doi.org/10.17232/KSET.32.3.487
  30. Yang, Y. C. (2004). The effects of embedded learning strategies to promote the use of self-regulated learning skills in a web-based learning environment. Journal of Educational Technology, 20(4), 3-23. https://doi.org/10.17232/KSET.20.4.3
  31. Shin, D. J. (2020). An Analysis Prospective Mathematics Teachers' Perception on the Use of Artificial Intelligence(AI) in Mathematics Education. Communications of Mathmatical Education, 34(3), 215-234.