College of Business

Increasing availability of digital libraries of K-12 curriculum resources, coupled with an increased emphasis on standard-based teaching necessitates assignment of the standards to the available curriculum. Since such assignment is a laborious and ongoing task, machine-based standard assignment tools have been under development for some time. Unfortunately, data on the performance of these machine-based classifiers are mostly lacking. In this paper we explore network modeling and layout to gain insight into the differences between human assignments and those by one of the better known machine-based classifiers. To build the standard assignment networks we define standards to be linked if they are jointly assigned to the same curricular item. Comparative analysis of the mapped networks shows that that unlike the machine-based assignment maps, the human-based maps elegantly reflect the rationales and principles of the assignment; i.e., clusters of standards separate along lines of lesson content and pedagogical principles. In addition, comparison of the maps clearly indicates that the machine classifier has trouble assigning so-called 'method' standards.