Text classification is the problem of assigning pre-defined class labels to incoming, unclassified documents. The class labels are defined based on a set of examples of pre-classified documents used as a training corpus. Various machine learning, information retrieval and probability based techniques have been proposed for text classification. In this paper we propose a novel, graph mining approach for text classification. Our approach is based onthe premise that representative -- common and recurring --structures/patterns can be extracted from a pre-classified document class using graph mining techniques and the same can be used effectively for classifying unknown documents. A number of factors that influence representative structure extraction and classification are analyzed conceptually and validated experimentally. In our approach, the notion of inexact graph match is leveraged for deriving structures that provide coverage for characterizing class contents. Extensive experimentation validate the selection of parameters and the effectiveness of our approach for tex tclassification. We also compare the performance of our approach with the naive Bayesian classifier.