Browse > Article
http://dx.doi.org/10.5392/JKCA.2021.21.10.001

Early Prediction Model of Student Performance Based on Deep Neural Network Using Massive LMS Log Data  

Moon, Kibum (고려대학교 디지털정보처)
Kim, Jinwon (고려대학교 디지털정보처)
Lee, Jinsook (고려대학교 디지털정보처)
Publication Information
The Journal of the Korea Contents Association / v.21, no.10, 2021 , pp. 1-10 More about this Journal
Abstract
Log data accumulated in the Learning Management System (LMS) provide high-quality information for the learning process of students. Until now, various studies have been conducted to predict students' academic achievement using LMS log data. However, previous studies were based on relatively small sample sizes of students and courses, limiting the possibility of generalization. This study developed and validated a deep neural network model for the early prediction of academic achievement of college students using massive LMS log data. To this end, we used 78,466,385 cases of LMS log data and 165,846 cases of grade data. The proposed model predicted the excellent-grade students with a high level of accuracy from the beginning of the semester. Meanwhile, the prediction accuracy for the moderate and underachieving groups was relatively low, but the accuracy improved as the time points of the prediction were delayed. This study is meaningful in that we developed an early prediction model based on a deep neural network with sufficient accuracy for practical utilization by only using LMS log data.
Keywords
Learning Management System; Student Success; Artificial Intelligence; Big Data; DNN;
Citations & Related Records
연도 인용수 순위
  • Reference
1 A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B.Steiner, Lu, F Bai, and S. Chintala, "PyTorch: An Imperative Style, High-Performance Deep Learning Library," In Advances in Neural Information Processing System, 32, pp.8024-8035, 2019.
2 교육부, "모든 학생을 위한 원격교육 환경 구축에 총력 - 원격교육 환경 구축을 위해 교육부.과학기술정보통신부 힘 모으기로 -," 보도자료, 2020.04.01.
3 M. Tietz, T. J. Fan, and D. Nouri, "skorch: A scikit-learn compatible neural network library that wraps PyTorch," July 2017. [Online]. Available: http://skorch.readthedocs.io
4 M. Riestra-Gonzalez, M. del Puerto Paule-Ruiz, and F. Ortin, "Massive LMS log data analysis for the early prediction of course-agnostic student performance," Computers & Education, Vol.163, 104108, 2021.   DOI
5 Y. Park and I. H. Jo, "Using log variables in a learning management system to evaluate learning activity using the lens of activity theory," Assessment and Evaluation in Higher Education, Vol.42, No.4 pp.531-547, 2017.   DOI
6 이해듬, "학습분석학 관점의 대학 이러닝 학습자 군집화와 학업성취도 관계 분석: 이러닝 학습 시.공간 데이터를 기반으로," 평생학습사회, 제14권, 제3호, pp.97-118, 2018.
7 J. G. Cromley, T. Perez, A. Kaplan, T. Dai, K. Mara, and M. J. Balsai, "Combined Cognitive-Motivational Modules Delivered Via an LMS Increase Undergraduate Biology Grades," Technology, Mind, and Behavior, Vol.1, No.2, 2020.
8 G. Van Rossum and F. L. Drake, Python 3 Reference Manual, Scotts Valley, CA: CreateSpace, 2009.
9 성한올, 조일현, "온라인 학습 상황에서 행동 로그, 생리심리반응 및 시험불안을 통한 멀티모달(Multimodal) 학업성취 예측모형 개발," 교육공학연구, 제34권, 제2호, pp.287-308, 2018.
10 F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michiel, B. Thirion, and O. Grisel, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, Vol.12, pp.2825-2830, 2011.
11 R. Conjin, C. Snijders A. Kleingeld, and U. Matzat, "Predicting Student Performance from LMS Data: A Comparison of 17 Blended Courses Using Moodle LMS," IEEE Transactions on Learning Technologies, Vol.10, No.1, pp.17-29, 2016.   DOI
12 C. R. Henrie, R. Bodily, R. Larsen, and C. R. Graham, "Exploring the potential of LMS log data as a proxy measure of student engagement," Journal of Computing in Higher Education, Vol.30, No.2 pp.344-362, 2018.   DOI
13 D. Kim, Y. Park, M. Yoon, and I. H. Jo, "Toward evidence-based learning analyrics: Using proxy variables to improve asynchronous online discussion environments," Internet and Higher Education, Vol.30, pp.30-43, 2016.   DOI
14 B. Rienties, L. Toetenel, and A. Bryan, ""Scaling up" learning design: impact of learning design activities on LMS behavior and performance," In Proceedings of the Fifth International Conference on Learning Analytics and Knowldege, pp.315-319, 2015.
15 이현진, "오토인코더에 기반한 딥러닝을 이용한 사이버대학교 학생의 학업 성취도 예측 분석 시스템 연구," 한국디지털콘텐츠학회 논문지, 제19권, 제6호, pp.1115-1121, 2018.
16 조일현, 김정현, "학습분석학을 활용한 e-러닝 학업성과 추정 모형의 통계적 유의성 확보 시점 규명," 교육공학연구, 제29권, 제2호, pp.285-306, 2013.
17 Y. H. Hu, C. L. Lo, and S. P. Shih, "Developing early warning systems to predict students' online learning performance," Computers in Human Behavior, Vol.36, pp.469-478, 2014.   DOI
18 유진은, "기계학습: 대용량/패널자료와 학습분석학 자료 분석으로의 활용," 교육공학연구, 제35권, 제2호, pp.313-338, 2019.
19 J. Heo, H. Lim, S. Yun, S. Ju, S. Park, and R. Lee, "Descriptive and Predictive Modeling of Student Achivement, Satisfaction, and Mental Health for Data-Driven Smart Connected Campus Life Service," In Proceedings of the 9th International Conference on Learning Analytics & Knowledge, pp.531-538, 2019.
20 이용상, 신동광, "코로나 19로 인한 언택트 시대의 온라인 교육 실태 연구," 교육과정평가연구, 제23권, 제4호, pp.39-57, 2020.
21 E. W. Black, D. Beck, K Dawson, S. Jinks, and M. DiPietro, "The other side of the LMS: Considering implementation and use in the adoption of an LMS in online and blended learning environments," TechTrends, Vol.51, No.2, pp.35-53, 2007.   DOI
22 조헌국, "머신 러닝을 활용한 이러닝 학습 환경에서의 학습자 성취 예측 모형 탐색," 학습자중심교과교육 연구, 제18권, 제21호, pp.553-572, 2018.