@article{eprints1097,
           pages = {28006},
       publisher = {IOPscience},
         journal = {EPL (Europhysics Letters)},
           month = {January},
          number = {2},
          volume = {81},
            year = {2008},
           title = {Taxonomy and clustering in collaborative systems: the case of the on-line encyclopedia Wikipedia},
          author = {Andrea Capocci and Francesco Rao and Guido Caldarelli},
             url = {http://eprints.imtlucca.it/1097/},
        abstract = {In this paper we investigate the nature and structure of the relation between imposed classifications and real clustering in a particular case of a scale-free network given by the on-line encyclopedia Wikipedia. We find a statistical similarity in the distributions of community sizes both by using the top-down approach of the categories division present in the archive and in the bottom-up procedure of community detection given by an algorithm based on the spectral properties of the graph. Regardless of the statistically similar behaviour, the two methods provide a rather different division of the articles, thereby signaling that the nature and presence of power laws is a general feature for these systems and cannot be used as a benchmark to evaluate the suitability of a clustering method.},
        keywords = {PACS: 89.75.Hc Networks and genealogical trees; 89.75.Fb Structures and organization in complex systems; 89.75.-k Complex systems}
}