结合学生行为模式分析的成绩早期预警研究

doi:10.3778/j.issn.1002-8331.2012-0365

摘要/Abstract

摘要： 早期预警是在线学习中的重要主题，通过早期预警识别有不及格风险的学生可帮助教师及时开展个性化教学干预。使用深度学习模型对学生微观行为模式进行分析以提高早期预警的效果，并提出结合LSTM-autoencoder特征处理和注意力权重计算的不及格风险学生早期预警模型（LSTM-autoencoder and attention based early warning model，LAA）。该方法通过LSTM-autoencoder对学生行为时间序列数据进行特征处理，采用注意力机制计算关键预测因子。实验结果表明，LAA比基线模型取得更高的召回率，对低交互型和非持续型学生具有更好的识别效果，且能将教学干预时间提前；此外，该方法可识别影响成绩的关键周次和行为，可用于辅助教师开展在线教学指导。

关键词: 在线学习, 学习行为模式, 早期预警, LSTM-autoencoder, 注意力机制

Abstract: Early warning is an important research topic in online learning. Identifying at-risk students through early warning can help teachers conduct personalized instructional interventions. This paper applies deep learning models for micro-level learning pattern analysis to improve early warning results, LAA（LSTM-autoencoder and attentionbased early warning model） is proposed. LSTM-autoencoder is used to process the feature of students’ behavior time series, the attention mechanism is used to calculate key predictors. The case study shows that LAA achieves higher recall rate than the baseline model, has unique strength in identifying low-interaction and non-persistent students, and advances the intervention time. In addition, LAA can identify the key weeks and behaviors for instructional intervention, which can help teachers in online learning activities.

Key words: online learning, learning pattern, early warning, LSTM-autoencoder, attention mechanism

张明焱, 杜旭, 李浩. 结合学生行为模式分析的成绩早期预警研究[J]. 计算机工程与应用, 2022, 58(1): 99-105.

ZHANG Mingyan, DU Xu, LI Hao. Research on Early Warning for Learning Performance Combined with Students’ Behavior Patterns Analysis[J]. Computer Engineering and Applications, 2022, 58(1): 99-105.

参考文献

[1] PAULE RUIZ M P，RIESTRA GONZáLEZ M，SáNCHEZ SANTILLáN M，et al.The procrastination related indicators in E-learning platforms[J].Journal of Universal Computer Science，2015，21（1）：7-22.
[2] AK?APINAR G J C.How automated feedback through text mining changes plagiaristic behavior in online assignments[J].Computers & Education，2015，87：123-130.
[3] KIM D，PARK Y，YOON M，et al.Toward evidence-based learning analytics：Using proxy variables to improve asynchronous online discussion environments[J].The Internet and Higher Education，2016，30：30-43.
[4] DU X，YANG J，SHELTON B E，et al.A systematic meta—Review and analysis of learning analytics research[J].Behaviour and Information Technology，2019，40（2）：1-14.
[5] SCHELL J，LUKOFF B，ALVARADO C.Using early warning signs to predict academic risk in interactive，blended teaching environments[J].Internet Learning，2014，3（2）：6.
[6] FARIA A M，SORENSEN N，HEPPEN J，et al.Getting students on track for graduation：Impacts of the early warning intervention and monitoring system after one year：REL 2017-272[R].2017.
[7] IVER M，STEIN M A，Davis M L，et al.An efficacy study of a ninth-grade early warning indicator intervention[J].Journal of Research on Educational Effectiveness，2019，12（3）：363-390.
[8] WANG H，LIU P.Application of improved association rule algorithm in early warning of student performance[J].Computer Engineering and Design，2015，3：679-682.
[9] AK?APINAR G，HASNINE M. N，MAJUMDAR R，et al.Developing an early-warning system for spotting at-risk students by using eBook interaction logs[J].Smart Learning Environments，2019，6（1）：4.
[10] HOWARD E，MEEHAN M，PARNELL A.Contrasting prediction methods for early warning systems at undergraduate level[J].The Internet and Higher Education，2018，37：66-75.
[11] HUNG J L，WANG M C，WANG S，et al.Identifying at-risk students for early interventions—A time-series clustering approach[J].IEEE Transactions on Emerging Topics in Computing，2017，5（1）：45-55.
[12] YANG X，LI J，XING B.Behavioral patterns of knowledge construction in online cooperative translation activities[J].The Internet and Higher Education，2018，36：13-21.
[13] ZHAO F，FENG J，ZHAO J，et al.Robust LSTM-autoencoders for face de-occlusion in the wild[J].IEEE Transactions on Image Processing，2017，27（2）：778-790.
[14] DU X，YANG J，HUNG J L.An integrated framework based on latent variational autoencoder for providing early warning of at-risk students[J].IEEE Access，2020，8：10110-10122.
[15] LI Y，FU C，ZHANG Y.When and who at risk？Call back at these critical points[C]//Proceedings of the International Educational Data Mining Society，2017.
[16] MALHOTRA P，RAMAKRISHNAN A，ANAND G，et al.LSTM-based encoder-decoder for multi-sensor anomaly detection[J].arXiv：1607.00148，2016.
[17] RAFFEL C，ELLIS D P.Feed-forward networks with attention can solve some long-term memory problems[J].arXiv：1512.08756，2015.
[18] KAHAN T，SOFFER T，NACHMIAS R.Types of participant behavior in a massive open online course[J].International Review of Research in Open and Distributed Learning，2017，18（6）：1-18.
[19] KENT C，LASLO E，RAFAELI S.Interactivity in online discussions and learning outcomes[J].Computers & Education，2016，97：116-128.
[20] SUN J C Y，LIN C T，CHOU C.Applying learning analytics to explore the effects of motivation on online students’ reading behavioral patterns[J].International Review of Research in Open and Distributed Learning，2018，19（2）：210-227.
[21] HUNG J L，SHELTON B E，YANG J，et al.Improving predictive modeling for at-risk student identification：A multistage approach[J].IEEE Transactions on Learning Technologies，2019，12（2）：148-157.
[22] YU L C，LEE C W，PAN H I，et al.Improving early prediction of academic failure using sentiment analysis on self-evaluated comments[J].Journal of Computer Assisted Learning，2018，34（4）：358-365.
[23] YANG Z K，YANG J，RICE K，et al.Using convolutional neural network to recognize learning images for early warning of at-risk students[J].IEEE Transactions on Learning Technologies，2020，13（3）：617-630.