AGG: Augmented Graph Grammars for Complex Heterogeneous Data

The central goal of educational datamining is to derive crucial pedagogical insights from student, course, and tutorial data. Real-world educational datasets are complex and heterogeneous comprising relational structures, social connections, demographic information, and long-term assignments. In this paper I describe Augmented Graph Grammars a robust formalism for graph rules that provides a natural structure for evaluating complex heterogeneous graph data. I also describe AGG an Augmented Graph Grammar engine written in Python and briefly describe its use.