TY - JOUR
T1 - Behavior-Based Grade Prediction for MOOCs Via Time Series Neural Networks
AU - Yang, Tsung Yen
AU - Brinton, Christopher G.
AU - Joe-Wong, Carlee
AU - Chiang, Mung
N1 - Funding Information:
Manuscript received October 15, 2016; revised March 1, 2017; accepted March 29, 2017. Date of publication May 2, 2017; date of current version July 18, 2017. This work was supported in part by Zoomi, Inc., under Grants NSF CNS-1347234 and ARO W911 NF-14-1-0190. The guest editor coordinating the review of this paper and approving it for publication was Prof. Mihaela van der Schaar. (Corresponding author: Christopher G. Brinton.) T. Y. Yang is with the Department of Electrical Engineering and Computer Science, National Chiao Tung University, Hsinchu 300, Taiwan (e-mail: tsungyenyang.eecs02@nctu.edu.tw).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8
Y1 - 2017/8
N2 - We present a novel method for predicting the evolution of a student's grade in massive open online courses (MOOCs). Performance prediction is particularly challenging in MOOC settings due to per-student assessment response sparsity and the need for personalized models. Our method overcomes these challenges by incorporating another, richer form of data collected from each student - lecture video-watching clickstreams - into the machine learning feature set, and using that to train a time series neural network that learns from both prior performance and clickstream data. Through evaluation on two MOOC datasets, we find that our algorithm outperforms a baseline of average past performance by more than 60% on average, and a lasso regression baseline by more than 15%. Moreover, the gains are higher when the student has answered fewer questions, underscoring their ability to provide instructors with early detection of struggling and/or advanced students. We also show that despite these gains, when taken alone, none of the behavioral features are particularly correlated with performance, emphasizing the need to consider their combined effect and nonlinear predictors. Finally, we discuss how course instructors can use these predictive learning analytics to stage student interventions.
AB - We present a novel method for predicting the evolution of a student's grade in massive open online courses (MOOCs). Performance prediction is particularly challenging in MOOC settings due to per-student assessment response sparsity and the need for personalized models. Our method overcomes these challenges by incorporating another, richer form of data collected from each student - lecture video-watching clickstreams - into the machine learning feature set, and using that to train a time series neural network that learns from both prior performance and clickstream data. Through evaluation on two MOOC datasets, we find that our algorithm outperforms a baseline of average past performance by more than 60% on average, and a lasso regression baseline by more than 15%. Moreover, the gains are higher when the student has answered fewer questions, underscoring their ability to provide instructors with early detection of struggling and/or advanced students. We also show that despite these gains, when taken alone, none of the behavioral features are particularly correlated with performance, emphasizing the need to consider their combined effect and nonlinear predictors. Finally, we discuss how course instructors can use these predictive learning analytics to stage student interventions.
KW - Clickstream data analysis
KW - MOOC
KW - learning analytics
KW - student performance prediction
UR - http://www.scopus.com/inward/record.url?scp=85029536665&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029536665&partnerID=8YFLogxK
U2 - 10.1109/JSTSP.2017.2700227
DO - 10.1109/JSTSP.2017.2700227
M3 - Article
AN - SCOPUS:85029536665
SN - 1932-4553
VL - 11
SP - 716
EP - 728
JO - IEEE Journal on Selected Topics in Signal Processing
JF - IEEE Journal on Selected Topics in Signal Processing
IS - 5
M1 - 7917237
ER -