Subverting structure: data-driven diagram generation

Diagrams are data representations that convey information predominantly through combinations of graphical elements rather than through other channels such as text or interaction. We have implemented a prototype called AVE (Automatic Visualization Environment) that generates diagrams automatically based on a generative theory of diagram design. According to this theory, diagrams are constructed based on the data to be visualized rather than by selection from a predefined set of diagrams. This approach can be applied to knowledge represented by semantic networks. We give a brief introduction to the underlying theory, then describe the implementation and finally discuss strategies for extending the algorithm