Section: Software

C-Quality

Participant : Jean-Charles Lamirel [correspondent] .

The C-Quality toolkit provides method-independent clustering quality measures and cluster labeling techniques specifically adapted to the interpretation of data analysis performed on textual data. The toolkit relies on an evaluation approach based on the exploitation of the maximized features of the data associated to each cluster after the clustering process without prior consideration of clusters profiles. The toolkit basic role is to act as an overall clustering quality evaluation tool. In a complementary way toolkit’s clusters labeling functionalities can be used altogether for visualizing or synthesizing clustering results, for optimizing learning of a clustering method, for validating cluster content and act as efficient variable selection methods in the framework of supervised or semi-supervised learning tasks.