Code-DKT: A Code-based Knowledge Tracing Model for Programming Tasks.
Identifying Common Errors in Open-Ended Machine Learning Projects
Automatic Student Code Modeling and Analysis
Just a Few Expert Constraints Can Help: Humanizing Data-Driven Subgoal Detection for Novice Programming
Early Performance Prediction using Interpretable Patterns in Programming Process Data
Identifying Struggling Students in Novice Programming Course with Knowledge Tracing
More with less: Exploring how to use deep learning effectively through semi-supervised learning for automatic bug detection in student code.
Proceedings of the 5th Workshop on Educational Data Mining in Computer Science Education @ EDM'21
Toward Semi-Automatic Misconception Discovery Using Code Embeddings
Comparing Feature Engineering Approaches to Predict Complex Programming Behaviors
Proceedings of the 4th Workshop on Educational Data Mining in Computer Science Education @ EDM'20