Thematic classification of Thomas Hardy’s work has traditionally been based partly on textual content and partly on biographical considerations. These analyses and criticisms have been generated by what will henceforth be referred to as ‘the philological method’, that is, by individual researcher’s reading of printed materials and the intuitive abstraction of generalizations from that reading. A major problem with studies in this tradition is that they are not objective or replicable. With the advent of electronic text, however, a large number of literary works, including the works of Thomas Hardy, have become available, and this electronic format now permits computational data analysis concepts and procedures to be applied to them. This makes it possible for thematic classifications of literary texts to be based to some degree on objective computational methods. In order to address issues of objectivity and replicability, this paper proposes an automated text clustering of the prose fiction works of Thomas Hardy using cluster analysis based on a vector space model (VSM) representation of the lexical content of the selected texts. The results reported here indicate that the proposed clustering structures yield usable results in understanding the thematic structure of Hardy’s prose fiction texts and that they and so in an objective and replicable way.