Leveraging Machine Learning and Natural Language Processing for Emotional and Thematic Analysis in Three Selected Contemporary English Novels

Abstract

The analysis of contemporary English novels, such as Sally Rooney's Normal People (2018), Yaa Gyasi's Homegoing (2016), and Khaled Hosseini's The Kite Runner (2003), offers a unique opportunity to explore the intersection of machine learning, deep learning, and natural language processing (NLP) within a post-humanist literary framework. This research paper employs computational techniques to examine how human experiences, emotions, and sociocultural dynamics are represented beyond traditional human-centric narratives. The post-humanist approach shifts focus from merely analyzing human emotions and character development to considering the agency of non-human elements—such as technology, culture, and the environment—in shaping narratives. Using sentiment analysis and emotion detection algorithms, the study investigates the contributions of these elements to the protagonists' emotional landscapes and how language reflects a broader, interconnected web of existence. It also explores narrative structure analysis and topic modeling to identify key themes highlighting the interplay between human and non-human actors in the texts. This includes examining how socio-political contexts and cultural artifacts influence character motivations, with an emphasis on relational dynamics within the narratives. Additionally, integrating deep learning models, such as transformer-based language models, facilitates a deeper understanding of semantic relationships and stylistic patterns. By analyzing figurative language and narrative techniques, the study reveals how the authors articulate complex themes of identity, displacement, and belonging in a world where human and non-human influences coexist. This post-humanist approach, which combines machine learning, deep learning, and NLP, enhances our appreciation of the emotional and thematic complexities in modern literature.