Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks

TL;DR

This paper introduces a novel graph-based approach to model Urdu novels as character interaction networks, enabling authorial style inference from narrative structure alone, and demonstrates its effectiveness with high accuracy on a dataset of Urdu novels.

Contribution

It pioneers the use of graph neural networks for authorial style analysis in Urdu literature by modeling narrative structure through character interaction graphs.

Findings

Graph neural networks outperform baselines in author identification.

Learned graph representations achieve up to 85.7% accuracy.

Narrative structure alone can reveal authorial style.

Abstract

Authorship analysis has traditionally focused on lexical and stylistic cues within text, while higher-level narrative structure remains underexplored, particularly for low-resource languages such as Urdu. This work proposes a graph-based framework that models Urdu novels as character interaction networks to examine whether authorial style can be inferred from narrative structure alone. Each novel is represented as a graph where nodes correspond to characters and edges denote their co-occurrence within narrative proximity. We systematically compare multiple graph representations, including global structural features, node-level semantic summaries, unsupervised graph embeddings, and supervised graph neural networks. Experiments on a dataset of 52 Urdu novels written by seven authors show that learned graph representations substantially outperform hand-crafted and unsupervised baselines, achieving up to 0.857 accuracy under a strict author-aware evaluation protocol.