Machine Learning Models For Some Learning Analytics Issues In Massive Open Online Courses

MPhil Thesis Defence


Title: "Machine Learning Models For Some Learning Analytics Issues In
Massive Open Online Courses"

By

Mr. Fei MI


Abstract

With the enormous scale of massive open online courses (MOOCs), many 
interesting learning analytics issues are worth studying. Peer grading is 
one vital issue for addressing the assessment challenge for open-ended 
assignments or exams while at the same time providing students with an 
effective learning experience through involvement in the grading process. 
Most existing MOOC platforms use simple schemes for aggregating peer 
grades, e.g., taking the median or mean. To enhance these schemes, some 
recent research attempts have developed machine learning methods under 
either the cardinal setting (for absolute judgment) or the ordinal setting 
(for relative judgment). In this thesis, we seek to study both cardinal 
and ordinal aspects of peer grading within a common framework. First, we 
propose novel extensions to some existing probabilistic graphical models 
for cardinal peer grading. Not only do these extensions give superior 
performance in cardinal evaluation, but they also outperform conventional 
ordinal models in ordinal evaluation. Next, we combine cardinal and 
ordinal models by augmenting ordinal models with cardinal predictions as 
prior. Such combination can achieve further performance boosts in both 
cardinal and ordinal evaluations, suggesting a new research direction to 
pursue for peer grading on MOOCs. Extensive experiments have been 
conducted using real peer grading data from a course offered by HKUST on 
the Coursera platform. As another learning analytics issue, dropout 
prediction is important due to the high attrition rate commonly seen on 
many MOOC platforms. Previous methods and current baselines use relatively 
simple machine learning models such as support vector machines and 
logistic regression. They use various features that reflect the student 
activities on a MOOC platform, including lecture video watching, forum 
activities etc. Since these features are captured continuously during the 
course period, dropout prediction is essentially a time series prediction 
problem. We propose to use a recurrent neural network model with long 
short-term memory cells to solve the dropout prediction problem. Extensive 
experiments conducted on both Coursera course and edX course offered by 
HKUST show significant improvement over other methods.


Date:			Wednesday, 27 May 2015

Time:			1:00pm - 3:00pm

Venue:			Room 2126B
 			Lift 19

Committee Members:	Prof. Dit-Yan Yeung (Supervisor)
 			Dr. Brian Mak (Chairperson)
 			Dr. Raymond Wong


**** ALL are Welcome ****