Reading Between the Lines: Exploring English Literature Through AI and Machine Learning

Abstract

The convergence of Artificial Intelligence (AI), Machine Learning (ML), and English literary studies marks a significant development in the growing field of Digital Humanities. Using tools such as Natural Language Processing (NLP), sentiment analysis, topic modeling, and stylometric analysis, scholars can now analyze literary texts with a scale and depth that were previously impossible. This paper examines how AI and ML enhance traditional literary criticism by uncovering hidden themes, stylistic patterns, and emotional trajectories across extensive collections of texts. This progress allows for both broad and detailed textual analysis. For example, stylometric research has shown up to 85% accuracy in distinguishing Shakespeare’s writing style from that of his peers (Jockers & Witten, 2010), providing empirical support for ongoing literary debates. Additionally, this study looks at how Large Language Models (LLMs) like GPT-4 can boost classroom engagement. These models can simulate character psychology, summarise complex stories, and assist with interpretative exercises. Applying sentiment analysis to the soliloquies in Hamlet can track Hamlet’s emotional decline in real time, helping students better understand character development. Interdisciplinary collaborations, such as initiatives at the Stanford Literary Lab, also show how AI can combine literary theory with data science, enabling the visualisation of character networks and genre shifts across centuries. Nonetheless, the integration of AI into literary studies is fraught with ethical and methodological challenges. AI tools frequently misinterpret nuances such as irony, symbolism, and cultural context, particularly in postcolonial texts such as Chinua Achebe’s Things Fall Apart. Additionally, issues surrounding authorship, originality, and algorithmic bias complicate AI’s role in literary scholarship. As T.S. Eliot astutely observed, “Genuine poetry can communicate before it is understood,” serving as a reminder that the profound meanings within literature often elude mechanistic interpretation.