Is there Method in Your Mistakes? Capturing Error Contexts by Graph Mining for Targeted Feedback
Maximilian Jahnke, Frank Höppner · Zenodo (CERN European Organization for Nuclear Research) · 2022
The value of an instructor is that she exactly recognizes what the learner is struggling with and provides constructive feedback straight to the point. This work aims at a step towards this type of feedback in the context of an introductory programming course, where students perform program execution tracing to align their understanding of Java instructions with reality. The students' submissions are analyzed for repeating mistakes across different exercises by representing the context surrounding the error by a graph and applying graph mining techniques to discover their common grounds. The patterns need to be annotated only once and help to address misconceptions of individual students. They may also be used to select follow-up exercises automatically, that contain the same intricacy.