Browsing into Data Masses: Graph Clustering and Visual Interpretation

Web Site: <a class="link" rel="nofollow" href="http://romain.raveaux.free.fr">http://romain.raveaux.free.fr</a><br /><br />A Clustering algorithm is applied on graphs and a visual interpretation is proposed.<br /><br />Model-Driven Engineering (MDE) promotes the use of models as first class<br />citizens. As a consequence, dealing with a wide variety of modeling languages<br />can be a cumbersome task. Developing tools and methods for dealing with its<br />variety of models is a challenging task for the MDE community. In this paper,<br />we propose a method for identifying families of modeling languages in<br />megamodels. This approach makes use of graph mining methods for automatically<br />labeled metamodels with a partitional clustering algorithm applied on a set of<br />features called graph probing. Metamodels tagged with the same labels form a<br />“Family” what is to say sharing common substructures. Finally, a<br />statistical cooccurrence matrix was computed on class names and association<br />roles to bring a semantic meaning to each metamodel family, building somehow a<br />tag cloud of the family.