This thesis concerns finding the 'optimal' number of (non-overlapping) word groups for text classification. We present a method to select which words to cluster in word groups and how many such word groups to use on the basis of a set of pre-classified texts. The method involves a greedy search through the space of possible word groups. The criterion on which is navigated through this space is based on 'mutual information' and is known as 'Jensen Shannon divergence'. The criterion to decide which number of word groups to use is based on Rissanen's MDL Principle. We present empirical results that indicate that the proposed method performs well at its task. The prediction model used is based on the Naive Bayes model and the data set used for the experiments is a subset of the 20 Newsgroup data set.