DOI QR코드

DOI QR Code

Improving learning outcome prediction method by applying Markov Chain

Markov Chain을 응용한 학습 성과 예측 방법 개선

  • Chul-Hyun Hwang (Dept. of BigData, HanYang Woman Univ)
  • 황철현 (한양여자대학 빅데이터과)
  • Received : 2024.04.20
  • Accepted : 2024.06.10
  • Published : 2024.07.31

Abstract

As the use of artificial intelligence technologies such as machine learning increases in research fields that predict learning outcomes or optimize learning pathways, the use of artificial intelligence in education is gradually making progress. This research is gradually evolving into more advanced artificial intelligence methods such as deep learning and reinforcement learning. This study aims to improve the method of predicting future learning performance based on the learner's past learning performance-history data. Therefore, to improve prediction performance, we propose conditional probability applying the Markov Chain method. This method is used to improve the prediction performance of the classifier by allowing the learner to add learning history data to the classification prediction in addition to classification prediction by machine learning. In order to confirm the effectiveness of the proposed method, a total of more than 30 experiments were conducted per algorithm and indicator using empirical data, 'Teaching aid-based early childhood education learning performance data'. As a result of the experiment, higher performance indicators were confirmed in cases using the proposed method than in cases where only the classification algorithm was used in all cases.

학습 성과를 예측하거나 학습 경로를 최적화하는 연구 분야에서 기계학습과 같은 인공지능 기술의 사용이 점차 증가하면서 교육 분야의 인공지능 활용은 점차 많은 진전을 보이고 있다. 이러한 연구는 점차 심층학습과 강화학습과 같은 좀 더 고도화된 인공지능 방법으로 진화하고 있다. 본 연구는 학습자의 과거 학습 성과-이력 데이터를 기반으로 미래의 학습 성과를 예측하는 방법을 개선하는 것이다. 따라서 예측 성능을 높이기 위해 Markov Chain 방법을 응용한 조건부 확률을 제안한다. 이 방법은 기계학습에 의한 분류 예측에 추가하여 학습자가 학습 이력 데이터를 분류 예측에 추가함으로써 분류기의 예측 성능을 향상 시키기 위해 사용된다. 제안 방법의 효과를 확인하기 위해서 실증 데이터인 '교구 기반의 유아 교육 학습 성과 데이터'를 활용하여 기존의 분류 알고리즘과 제안 방법에 의한 분류 성능 지표를 비교하는 실험을 수행하였다. 실험 결과, 분류 알고리즘만 단독 사용한 사례보다 제안 방법에 의한 사례에서 더 높은 성능 지표를 산출한다는 것을 확인할 수 있었다.

Keywords

References

  1. L. Chen, P. Chen and Z. Lin, "Artificial Intelligence in Education: A Review," in IEEE Access, vol. 8, pp. 75264-75278, 2020, doi: 10.1109/ACCESS.2020.2988510. 
  2. Chul-Hyun Hwang, "Improvement of early prediction performance of under-performing students using anomaly data," Journal of the Korea Institute of Information and Communication Engineering(JKIICE), Vol. 26, No. 11, pp. 1608-1614, Dec 2022, DOI : 10.6109/jkiice.2022.26.11.1608 
  3. H. Lakkaraju, E. Aguiar, C. Shan, D. Miller, N. Bhanpuri, R. Ghani, and K. L. Addison, "A Machine Learning Framework to Identify Students at Risk of Adverse Academic Outcome," in Proceedings of the 21st ACM SIGKDD, International Conference on Knowledge Discovery and Data, Sydney, Australia, pp. 1909-1918, 2015. 
  4. B. Albreiki, N. Zaki, and H. Alashwal, "A Systematic Literature Review of Student' Performance Prediction Using Machine Learning Techniques," Education Science, vol. 11, no. 9, pp. 1-27, Sep. 2020. 
  5. E. Alyahyan and D. Dustegor, "Predicting academic success in higher education: Literature review and best practices," International Journal of Educational Technology in Higher Education, vol. 17, no. 3, Feb. 2020. 
  6. W. Xing and D. Du, "Dropout Prediction in MOOCs: Using Deep Learning for Personalized Intervention", Journal of Educational Computing Research, vol. 57, no. 3, pp. 547-570, Mar. 2019. 
  7. T. A. Mikropoulos and A. Natsis, "Educational virtual environments: A ten-year review of empirical research (1999-2009)", Comput. Edu., vol. 56, no. 3, pp. 769-780, Apr. 2011. 
  8. Chunhong Liu, Haoyang Zhang, Jieyu Zhang, Zhengling Zhang, Peiyan Yuan, "Design of a Learning Path Recommendation System Based on a Knowledge Graph", International Journal of Information and Communication Technology Education (IJICTE), Vol. 19, Issue. 1, pp. 1-18, Dec 2023, , DOI : 
  9. Eunjung Lee, Youngsoo Song, Jiha Kim, Suhyun Oh," An Exploratory Study on Determinants Predicting the Dropout Rate of 4-year Universities Using Random Forest: Focusing on the Institutional Level Factors", Journal of Educational Technology, Vol. 36, No. 1, pp.191 -219, 2020, , DOI: 10.17232/KSET.36.1.191 
  10. Chunhong Liu, Haoyang Zhang, Jieyu Zhang, Zhengling Zhang, Peiyan Yuan, "Design of a Learning Path Recommendation System Based on a Knowledge Graph", International Journal of Information and Communication Technology Education (IJICTE), Vol. 19, Issue. 1, pp. 1-18, Dec 2023, , DOI : 10.4018/IJICTE.319962 
  11. Yeon-Hee Kim, Soo-Jin Lim, "A Study on the Prediction of Learning Results Using Machine Learning", Jounal of Educational Technology, vol 36, No 1, pp. 191-219, July 2020 
  12. Lee Jae Kyu , PARK HEESUNG , Wo j Kim, "Major Class Recommendation System based on Deep learning using Network Analysis", Journal of Intelligence and Information Systems(JIIS), Vol. 27, No. 1, pp. 95-112, Dec 2023 
  13. Oakyoung Han, "A Study on Components for Designing Personalized Education Systems Based on Generative AI", The Journal of Korean association of computer education, vol 26, No 6, pp. 127-141, Oct 2023 
  14. Hyeon-Seong Kim, Jin-Seok Kim, "A Study on Regional-customized education program selection model using big data analysis", The Journal of the Convergence on Culture Technology (JCCT), Vol. 9 No. 2, Mar, 2023 
  15. Siemens. G, Long. P, "Penerrating the foganalytics in learning and educations." Education Review, Vol.46, No.5, pp.30-32, 2011.