We present a novel approach to the automated marking of student programming assignments. Our technique quantifies the structural similarity between unmarked student submissions and marked solutions, and is the basis by which we assign marks. This is accomplished through an efficient novel graph similarity measure ("AssignSim"). Our experiments…

Describes CAPA, a software tool to implement a computer-assisted personalized approach for homework assignments and examinations in a large introductory physics class at Michigan State University. Highlights include increased individual attention for students; correlation between homework performance and results of the final exam; feedback for…