Identifying and Responding to Disengagement in a Constraint-Based Intelligent Tutoring System

Numerous studies have shown the effectiveness of Intelligent Tutoring Systems in improving learning. However, there are still students who do not engage with problem solving and therefore miss opportunities for learning. In my project, I am investigating whether it is possible to predict when the student would abandon a problem, thus allowing the system to try to motivate the student to persevere. I will discuss the approach taken to generate a predictor, including identifying the features from log data and the selection of the learning algorithm to produce a predictor. To demonstrate the accuracy of the generated decision tree predictor, we conduct an experiment deploying this predictor in a study with SQL-Tutor.