Educational Data Mining (EDM) and Learning Analytics (LA) are emerging fields of study in learning technology. EDM and LA seek to identify the patterns in the characteristics of learners recorded in a large-scale educational data (e.g., students’ use of interactive learning environment, computer-supported collaborative learning or administrative data from schools). Using the identified patterns, EDM and LA try to better understand students, their learning outcomes, and the learning environment. Learning Technologies faculty, such as Dr. Youngjin Lee, applied various EDM and LA algorithms and techniques, (e.g., Self-Organizing Map (SOM), TrueSkill, Item Response Theory (IRT), Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine (SVM), etc.), to clickstream log files capturing how students enrolled in MOOCs interact with various learning resources in order to identify learning behaviors of students that predict their learning performance and academic success.
For further reading on educational data mining and learning analytics, please see below:
- Lee, Y. (2019). Estimating student ability and problem difficulty using Item Response Theory (IRT) and TrueSkill. Information Discovery and Delivery, 47(2), 67–75.
- Lee, Y. (2018). Using Self-Organizing Map (SOM) and clustering to investigate problem solving patterns in the Massive Open Online Course (MOOC): An exploratory study. Journal of Educational Computing Research, 57(2), 471–490. Lee, Y. (2016). Predicting students’ problem solving performance using Support Vector Machine. Journal of Data Science, 14, 231–244.