Extension of the fuzzy c means clustering algorithm to fit with the composite graph model for web document representation

Clustering techniques are mostly unsupervised methods that can be used to organize data into groups based on similarities among the individual data items. Fuzzy c-means (FCM) clustering is one of well known unsupervised clustering techniques, which can also be used for unsupervised web document clustering. In this chapter we will introduce a modified method of clustering where the data to be clustered will be represented by graphs instead of vectors or other models. Specifically, we will extend the classical FCM clustering algorithm to work with graphs that represent web documents [1,2,3]. We wish to use graphs because they can allow us to retain information which is often discarded in simpler models.