面向长短期混合数据的MOOC辍学预测策略研究

doi:10.3778/j.issn.1002-8331.2108-0375

摘要/Abstract

摘要： 针对MOOC中学生行为数据的长短期混合特性，为解决辍学预测中的动态类别不平衡问题，提出一种基于深度学习的辍学预测策略。首先建立以天为时间步长、周为学习周期的新型学生行为时间序列，以捕捉每一时间步长下时间序列数据的短期依赖关系和相邻学习周期之间的长期模式和趋势。然后结合辍学定义的两种不同表达揭示MOOC辍学预测的动态类别不平衡现象。接着引入基于代价敏感的长短期时间序列深度学习模型，以实现对高辍学风险学生的精准预测。最后在KDD Cup 2015数据集上的实验证明，所提策略能够有效帮助MOOC课程教师和教学管理者追踪课程学生在不同时间步长的学习状态，从而动态监控不同学习阶段的辍学行为。

关键词: 大规模开放式在线课程（MOOC）, 深度学习, 辍学预测, 时间序列模型, 代价敏感性学习

Abstract: Aiming at the problems of long- and short-term mixed characteristics and dynamic class imbalance of students’ behavior data in MOOC, a dropout prediction strategy based on deep learning is proposed. Firstly, a novel time series of student’ behavior is established with days as time steps and weeks as learning cycles, which can capture the short-term dependence of each time step, and acquire long-term patterns between adjacent learning cycles. Then, two different expressions of the dropout definition are combined to reveal the dynamic class imbalance phenomenon. Subsequently,?the long- and short-term time series model based on cost-sensitive learning is introduced to predict high dropout risk students accurately. Finally, experimental results on KDD Cup 2015 dataset indicate that the proposed strategy can effectively help MOOC teachers and administrators to track the learning status of learners at different time steps, and dynamically monitor dropout behavior at different learning stages.

Key words: massive open online courses（MOOC）, deep learning, dropout prediction, time series model, cost-sensitive learning

杨坤融, 熊余, 张健, 储雯. 面向长短期混合数据的MOOC辍学预测策略研究[J]. 计算机工程与应用, 2023, 59(4): 130-138.

YANG Kunrong, XIONG Yu, ZHANG Jian, CHU Wen. Research on MOOC Dropout Prediction Strategy for Long- and Short-Term Mixed Data[J]. Computer Engineering and Applications, 2023, 59(4): 130-138.

参考文献

[1] 于歆杰.从交互到融合：新冠肺炎疫情的高等教育应对之策[J].中国电机工程学报，2020，40（20）：6411-6418.
YU Y J.From interaction to integration：higher education response to the new coronal pneumonia epidemic[J].Proceedings of the CSEE，2020，40（20）：6411-6418.
[2] 林鹏飞，何秀青，陈甜甜，等.深度学习视阈下MOOC学生流失预测及干预研究[J].计算机工程与应用，2019，55（22）：258-264.
LING P F，HE X Q，CHEN T T，et al.Prediction of loss and teaching intervention for learners in MOOC from perspective of deep learning[J].Computer Engineering and Applications，2019，55（22）：258-264.
[3] KHALIL H，EBNER M.MOOCs completion rates and possible methods to improve retention—a literature review[C]//World Conference on Educational Multimedia，Hypermedia and Telecommunications，2014：1305-1313.
[4] 李梦莹，王晓东，阮书岚，等.基于双路注意力机制的学生成绩预测模型[J].计算机研究与发展，2020，57（8）：1729-1740.
LI M Y，WANG X D，RUAN S L，et al.Students performance prediction model based on two-way attention mechanism[J].Journal of Computer Research and Development，2020，57（8）：1729-1740.
[5] FENG W，TANG J，LIU T X.Understanding dropouts in MOOCs[C]//Proceedings of the AAAI Conference on Artificial Intelligence，Hawaii，2019：517-524.
[6] GARDNER J，BROOKS C.Dropout model evaluation in MOOCs[C]//Proceedings of the AAAI Conference on Artificial Intelligence，Louisiana，2018：7906-7912.
[7] AMNUEYPORNSAKUL B，BHAT S，CHINPRUTTHIWONG P.Predicting attrition along the way：the UIUC model[C]//Proceedings of the EMNLP 2014 Workshop on Analysis of Large Scale Social Interaction in MOOCs，Doha，2014：55-59.
[8] KLOFT M，STIEHLER F，ZHENG Z，et al.Predicting MOOC dropout over weeks using machine learning methods[C]//Proceedings of the EMNLP 2014 Workshop on Analysis of Large Scale Social Interaction in MOOCs，Doha，2014：60-65.
[9] FEI M，YEUNG D Y.Temporal models for predicting student dropout in massive open online courses[C]//2015 IEEE International Conference on Data Mining Workshop，2015：256-263.
[10] WEN Y M，TIAN Y，WEN B X，et al.Consideration of the local correlation of learning behaviors to predict dropouts from MOOCs[J].Tsinghua Science and Technology，2020，25（3）：336-347.
[11] WU N，ZHANG L，GAO Y，et al.CLMS-Net：dropout prediction in MOOCs with deep learning[C]//Proceedings of the ACM Turing Celebration Conference，2019：1-6.
[12] 张阳，鲁鸣鸣，郑一基，等.基于图自编码器模型的学生成绩预测[J].计算机工程与应用，2021，57（13）：251-257.
ZHANG Y，LU M M，ZHENG Y J，et al.Student grade prediction based on graph auto-encoder model[J].Computer Engineering and Applications，2021，57（13）：251-257.
[13] LAI G，CHANG W C，YANG Y，et al.Modeling long-and short-term temporal patterns with deep neural networks[C]//Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval，2018：95-104.
[14] 罗恒，杨婷婷，伊丽莎·理查德森，等.开放课程中的学习行为分析：来自Google Analytics的证据[J].中国电化教育，2017（10）：8-14.
LUO H，YANG T T，ELIZA R.Analysis of learning behaviors in an open course：evidence from Google Analytics[J].China Educational Technology，2017（10）：8-14.
[15] LóPEZ V，FERNáNDEZ A，GARCíA S，et al.An insight into classification with imbalanced data：empirical results and current trends on using data intrinsic characteristics[J].Information Sciences，2013，250：113-141.
[16] SUNAR A S，WHITE S，ABDULLAH N A，et al.How learners’ interactions sustain engagement：a MOOC case study[J].IEEE Transactions on Learning Technologies，2017，10（4）：475-487.
[17] 张国豪，刘波.采用CNN和Bidirectional GRU的时间序列分类研究[J].计算机科学与探索，2019，13（6）：916-927.
ZHANG G H，LIU B.Research on time series classification using CNN and Bidirectional GRU[J].Journal of Frontiers of Computer Science and Technology，2019，13（6）：916-927.
[18] IOFFE S，SZEGEDY C.Batch normalization：accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning，Lille，2015：448-446.
[19] RAJ V，MAGG S，WERMTER S.Towards effective classification of imbalanced data with convolutional neural networks[C]//IAPR Workshop on Artificial Neural Networks in Pattern Recognition.Cham：Springer，2016：150-162.
[20] KINGMA D P，BA J.Adam：a method for stochastic optimization[C]//International Conference on Learning Representations，2015：1-15.
[21] FRIEDMAN J H.Greedy function approximation：a gradient boosting machine[J].Annals of Statistics，2001，29（5）：1189-1232.
[22] HE J，BAILEY J，RUBINSTEIN B，et al.Identifying at-risk students in massive open online courses[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2015，29：1-12.