This paper describes an automatization of the clustering of conceptual diagrams through the definition of semantic distances between concepts, and through the use of a clustering algorithm. For entity-relationship clustering, we define three different distances (visual, hierarchical and cohesive), depending on the semantic richness of the model. Object model clustering is based on the structural, semantic and communicational characteristics of objects.
AKOKA, J. and COMYN-WATTIAU, I. (1996). Entity-relationship and Object-oriented Model Automatic Clustering. Data and Knowledge Engineering, pp. 87-117.