Abstract

This paper explores the application of computational stylometry to analyze the evolution of authorial voice in 21st-century novels. We investigate how machine learning algorithms can identify and track stylistic markers, revealing subtle shifts in writing style across an author's oeuvre or within a single novel. By examining quantifiable features like word frequency, sentence structure, and punctuation patterns, we aim to understand how authors adapt their voice in response to various factors, including evolving literary trends, reader expectations, and personal stylistic development. Our analysis focuses on a selection of contemporary novels, employing diverse computational methods to uncover patterns and insights that may not be readily apparent through traditional literary criticism. The findings contribute to a deeper understanding of the dynamic nature of authorial voice in the digital age and demonstrate the potential of computational stylometry to enrich literary scholarship.