Towards Computational Models to Theme Analysis in Literature

The recent years have witnessed the development of numerous computational methods that have been widely used in humanities and literary studies. In spite of their potentials of such methods in terms of providing workable solutions to different inherent problems within these domains including selectivity, objectivity, and replicability, very little has been done on thematic studies in literature. Almost all the work is done through traditional methods based on individual researchers’ reading of texts and intuitive abstraction of generalizations from that reading. These approaches have negative implications to issues of objectivity and replicability. Furthermore, it is challenging for such traditional methods to deal effectively with the hundreds of thousands of new novels that are published every year. In the face of these problems, this study proposes an integrated computational model for the thematic classifications of literary texts based on lexical clustering methods. As an example, this study is based on a corpus including Thomas Hardy’s novels and short stories. Computational semantic analysis based on the vector space model (VSM) representation of the lexical content of the texts is used. Results indicate that the selected texts were thematically grouped based on their semantic content. It can be claimed that text clustering approaches which have long been used in computational theory and data mining applications can be usefully used in literary studies.