Paper on providing personalized feedback in programming MOOCs to appear at ICDE 2017
Computer Science PhD student Victor J. Marin, Computer Science Master's student Tobin Pereira, Srinivas Sridharan at Stevens Institute of Technology, USA (former Computer Science PhD student), and Carlos R. Rivero will present their paper entitled "Automated Personalized Feedback in Introductory Java Programming MOOCs" in ICDE 2017, a top-tier international conference on data engineering. The conference will be held in San Diego, California this coming April.
The paper describes a new technique to provide personalized feedback in introductory programming MOOCs devised at the Graph-Oriented AppLications Research Lab (GOAL Lab). This is going to be the main research focus of the GOAL Lab in the next years and the main topic of Victor J. Marin's research.
The paper describes a semantic-aware technique for providing personalized feedback that aims to mimic an instructor looking for code snippets in student submissions. These snippets are modeled as subgraph patterns with natural language feedback attached to them. Submissions are transformed into extended program dependence graphs combining control and data flows. It leverages subgraph matching techniques to compute the adequate personalized feedback. Also, constraints correlating patterns allow performing fine-grained assessments.