Towards Computational Models to Theme Analysis in Literature

Abdulfattah Omar

doi:10.14569/ijacsa.2020.0110911

Abstract

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.

Highlights

An important development in literary studies over the past few decades is the increasing application of scientific methods in analysis of literary works [1,2,3,4,5]
It has been argued that the use of such scientific methods can assist in preventing the formation of false theories of criticism and the generation of unreliable thematic classifications [6, 7]
This study addressed the question whether thematic concepts can be identified in literary texts using computational models

Summary

INTRODUCTION

An important development in literary studies over the past few decades is the increasing application of scientific methods in analysis of literary works [1,2,3,4,5]. The study seeks to propose a computational model that helps readers and critics of literary texts in an objective, replicable, scientific way through exploring the thematic relationships of texts in a conceptually coherent way. The study is an attempt towards bridging the gap between traditional literary criticism and computational methods. It describes document clustering methods are used to classify the selected works in a thematically coherent way. It summarizes the main findings and suggests propositions that may be generalized to other literary texts and genres

LITERATURE REVIEW

METHODS AND PROCEDURES

ANALYSIS AND DISCUSSIONS

CONCLUSION