Cognitive diagnostic like approaches using neural-network analysis of serious educational videogames

There has been an increase in student achievement testing focusing on content and not underlying student cognition. This is of concern as student cognition provided for a more generalizable analysis of learning. Through a cognitive diagnostic approach, the authors model the propagation of cognitive attributes related to science learning using Serious Educational Games. One-way to increase the focus on the cognitive aspects of learning that are additional to content learning is through the use cognitive attribute task-based assessments (Cognitive Diagnostics) using an Artificial Neural Network. Results of this study provide a means to examine underlying cognition which, influences successful task completion within science themed SEGs. Results of this study also suggest it is possible to define, measure, and produce a hierarchical model of latent cognitive attributes using a Q-matrix relating virtual SEGs tasks, which are similar to real-life tasks aiding in the modeling of transference.