Evaluation of Automatically Generated Hint Feedback

This work explores the effects of using automatically generated hints in problem solving tutor environments. Generating hints automatically removes a large amount of development time for new tutors, and it also useful for already existing computer-aided instruction systems that lack intelligent feedback. We focus on a series of problems, after which, previous analysis showed the control group is to be 3.5 times more likely to cease logging onto an online tutor when compared to the group who were given hints. We found a consistent trend in which students without hints spent more time on problems when compared to students that were provided hints.