The q-matrix method is proposed, where data from student behavior is “mined” to create concept models of the material being taught, and preliminary results imply that the method can effectively predict which concepts need further review.
The feasibility of this approach to automatically generate hints for an intelligent tutor that learns is demonstrated by extracting MDPs from four semesters of student solutions in a logic proof tutor, and the probability that they will be able to generate hints at any point in a given problem is calculated.
The philosophy of the Beauty and Joy of Computing, an update on the course design principles, a general flow through the authors' curriculum, the impact BJC has had, and lessons learned are shared.
Wu's Castle is a game where students program changes in loops and arrays in an interactive, visual way that helps students visualize code execution in a safe environment and suggests that games like Wu's Castle can help prepare students to create deeper, more robust understanding of computing concepts while improving their perceptions of computing homework assignments.
The results demonstrate that Astrojumper effectively motivates both children and adults to exercise through immersive virtual reality technology and a simple, yet engaging, game design.
This dissertation resulted in the construction of a fully automated, fault tolerant, intelligent tutoring system, which can diagnose and correct student misconceptions.
A novel, data-driven algorithm for generating feedback for students on open-ended programming problems, which goes beyond next-step hints, annotating a student’s whole program with suggested edits, including code that should be moved or reordered.
This work augmented the Deep Thought logic tutor with a Hint Factory that generates data-driven, context-specific hints for an existing computer aided instructional tool, and shows that hints help students persist in a deductive logic proofs tutor.
Results show that this method of building games to teach engages students at multiple levels, inspiring newer students that one day their homework may all be games, and encouraging advanced students to continue on into graduate studies in computing.
The findings indicate that the language produced by students can predict with substantial accuracy whether students complete the MOOC, which suggests that NLP can help to understand student retention in MOOCs and to develop automated signals of student success.