Graph Analysis of Student Model Networks

This paper explores the feasibility of a graph-based approach to model student knowledge in the domain of programming. The key idea of this approach is that programming concepts are truly learned not in isolation, but rather in combination with other concepts. Following this idea, we represent a student model as a graph where links are gradually added when the student’s ability to work with connected pairs of concepts in the same context is confirmed. We also hypothesize that with this graph-based approach a number of traditional graph metrics could be used to better measure student knowledge than using more traditional scalar models of student knowledge. To collect some early evidence in favor of this idea, we used data from several classroom studies to correlate graph metrics with various performance and motivation metrics