Using Bugs in Student Code to Predict Need for Help

摘要: Code Puzzles can be an engaging way to learn programming concepts, but getting stuck in a puzzle discouraging when no help or feedback is available. Teachers and facilitators alleviate this problem classroom setting, it hard for teachers keep track of who needs likely resolve their on own, especially large classroom. This work step toward helping optimize time by automatically gauging which students may benefit from intervention at any given time. We use information about the bugs present student code predict are more abandon take too long solving it. Ultimately, we envision that could these predictions make decisions whom they should next, how.