Computational analysis of dystopian elements in the partition fiction: A machine learning approach to the indian English novels

Aug 4, 2026

Upload by Noah

Despite growth in digital humanities, computational methods for analyzing literary themes and dystopian elements remain limited. This study applies machine learning text classification to seven Indian English Partition novels, aiming to build and implement an opinion mining framework to identify and categorize dystopian elements, then assess model effectiveness for dystopian sentiment classification. The workflow includes six phases from data collection and preprocessing through text extraction, exploration, modeling/classification, and performance evaluation. Logistic Regression, Naïve Bayes, SVM, and k-Nearest Neighbor are compared.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Computational methods and text classification

Methodology

Opinion mining framework workflow

Data preprocessing and text extraction

Supervised machine learning classification

Results

Key dystopian elements identified

Classifier comparison and performance

Discussion

Feature representation: CountVectorizer vs TF-IDF

Social Sciences & Humanities Open 10 (2024) 100897 Contents lists available at ScienceDirect Social Sciences & Humanities Open journal [homepage: www.sciencedirect.com/journal/social-sciences-and-humanities-open](homepage: www.sciencedirect.com/journal/social-sciences-and-humanities-open) | Regular Article
Computational analysis of dystopian elements in the partition fiction: A machine learning approach to the indian English novels
Atina Najahan Binti Mohd Rashidic, Pantea Keikhosrokiania, *, Moussa Pourya Aslb, Henry Oinas-Kukkonen b
a Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland b Faculty of Humanities, University of Oulu, Finland
c School of Computer Sciences, Universiti Sains Malaysia, 11800, Minden, Penang, Malaysia | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords: Dystopia Opinion mining Text analytics
Text classification
Supervised machine learning | | Despite the growth of digital humanities, the specific application of computational methods to analyse literary themes and elements remains underexplored. This study aims to use machine learning algorithms for text classification on seven novels about the partition of India. The article has a dual objective: firstly, to develop and implement an innovative opinion mining framework that leverages machine learning techniques to identify and classify dystopian elements in Partition novels; and secondly, to evaluate and compare the efficacy of the model in accurately classifying dystopian sentiments within selected literary texts. The proposed framework includes six phases of data collection, test-pre-processing, text extraction, text exploration, modelling or classification using machine leaning, and performance evaluation. Machine learning approaches such as Logistic Regression, Naïve Bayes, Support Vector Machine, and k-Nearest Neighbor are adopted to classify the text based on compiled dictionary. First, the study revealed that the main components and characteristics of dystopian elements found in selected narratives are ‘fear’, ‘suffer’,‘oppression’ and ‘violence’. Second, the analysis showed that SVM with CountVectorizer, using imbalanced dataset and random oversampling dataset, outperforms other classifiers in classifying dystopian types in the selected novels. The results also suggest that CountVectorizer works better for the dataset compared to TF-IDF. | 1. Introduction Over the past two decades, advancements in information technology and data sciences have led scholars of various disciplines to replace conventional and manual modes of analysis with computerized techniques and methods. Machine learning models such as natural language processing (NLP) is one of the most popular approaches within the field of humanities (Keikhosrokiani & Asl, 2022a, b; Al Mamun et al., 2022). As a machine learning technique, text classification is an approach to NLP that sheds light on the underlying sentiment and emotion within a text. This study employs a text classification method to examine a corpus of literary texts on the Partition of India with the aim of classifying the key elements and sentiments that help to label such narratives as dystopian. To achieve this primary goal, the study pursues three objectives: (1) to compile a reference dictionary by identifying dystopian elements in selected novels on Partition of India,(2) to predict dystopian types in selected literally works using machine learning and the compiled dictionary (3) to compare different machine learning algorithms based on the accuracy for the classification of dystopian elements. Dystopia is literally defined as “an imaginary place or state in which everything is extremely bad or unpleasant”(Oxford, n.d). It is described as an anti-utopia that conjures up images of terrifying futures filled with chaos and disaster (Asl, 2018, 2022; Claeys, 2016). Dystopian fiction is a genre that seeks to depict t

FAQs

What is the study’s main goal for analyzing Partition novels?

To use machine learning to classify dystopian elements and sentiments in seven novels about the Partition of India, supported by an opinion mining framework.

How does the proposed framework work from data to evaluation?

It follows six phases: data collection, test preprocessing, text extraction, text exploration, machine-learning modeling/classification, and performance evaluation.

Which dystopian elements are found as the dominant components in the selected narratives?

The main components identified are ‘fear’, ‘suffer’, ‘oppression’, and ‘violence’.

Aug 4, 2026

Upload by Noah