Predicting Learning Effect by Learner's Behavior in MOOCs

With the fast development of MOOCs in recent years, more and more people start to take MOOCs to perfect themselves. However, there exist high dropout rate and low passing rate of examination in many courses. So it is very important to predict learners’ learning effect exactly. For learners who predicted good learning effect, teachers can impose intervention to help these learners to stick to the end of courses, while for predicted bad learning effect, teachers can take measures to help these learners to study harder to improve their learning. In this paper, we first analyze learners’ learning behavior data to explore the differences among learners with different categories, then a cascade prediction model is proposed to predict whether a learner can earn certificate in a course. Experiments conducted on a real-world dataset illustrated the effectiveness of the proposed model.

[1]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.

[2]  Justine Cassell,et al.  Connecting the Dots: Predicting Student Grade Sequences from Bursty MOOC Interactions over Time , 2015, L@S.

[3]  Zhang Yan,et al.  Learning Behavior Analysis and Prediction Based on MOOC Data , 2015 .

[4]  J. Prabakaran,et al.  Massive Open Online Course , 2014 .

[5]  Gustavo E. A. P. A. Batista,et al.  Class Imbalances versus Class Overlapping: An Analysis of a Learning System Behavior , 2004, MICAI.

[6]  Niels Pinkwart,et al.  Predicting MOOC Dropout over Weeks Using Machine Learning Methods , 2014, EMNLP 2014.

[7]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[8]  Deepti Mehrotra,et al.  Performance analysis of student learning metric using K-mean clustering approach K-mean cluster , 2016, 2016 6th International Conference - Cloud System and Big Data Engineering (Confluence).

[9]  Dit-Yan Yeung,et al.  Temporal Models for Predicting Student Dropout in Massive Open Online Courses , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[10]  Justin Reich,et al.  HarvardX and MITx: The First Year of Open Online Courses, Fall 2012-Summer 2013 , 2014 .

[11]  Yoav Bergner,et al.  Who does what in a massive open online course? , 2014, Commun. ACM.

[12]  George Karypis,et al.  Predicting Student Performance Using Personalized Analytics , 2016, Computer.

[13]  Haoran Xie,et al.  A Big Data Framework for Early Identification of Dropout Students in MOOC , 2015 .

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Stephen Kwek,et al.  Applying Support Vector Machines to Imbalanced Datasets , 2004, ECML.

[16]  Qian Zhang,et al.  Modeling and Predicting Learning Behavior in MOOCs , 2016, WSDM.