Abstract
Thematic studies in literature have traditionally been based on philological methods supported by personal knowledge and evaluation of the texts. A major problem with studies in this tradition is that they are not objective or replicable. With the development of digital technologies and applications, it is now possible for theme analysis in literary texts to be based at least partially on objective replicable methods. In order to address issues of objectivity and replicability in thematic classification of literary text, this study proposes a computational model to theme analysis of the poems of Emily Dickinson using cluster analysis based on a vector space model (VSM) representation of the lexical content of the selected texts. The results indicate that the proposed model yields usable results in understanding the thematic structure of Dickinson's prose fiction texts and that they do so in an objective and replicable way. Although the results of the analysis are broadly in agreement with existing, philologically-based critical opinion about the thematic structure of Dickinson's work, the contribution of this study is to give that critical opinion a scientific, objective, and replicable basis. The methodology used in this study is mathematically-based, clear, objective, and replicable. Finally, the results of the study have their positive implications to the use of computational models in literary criticism and literature studies. The success of computer-aided approaches in addressing inherent problems in the field of literary studies related to subjectivity and selectivity argues against the theoretical objections to the involvement of computer and digital applications in the study of literature.