Sigrid Kim
Viennart Academy
Abstract
The advent of digital tools and methods has transformed literary criticism, enhancing traditional
analysis through techniques such as text mining, sentiment analysis, and topic modeling. This paper
explores the role of these tools in modern literary analysis, demonstrating their potential through
case studies. Text mining, for example, helps researchers uncover hidden patterns in literary works,
as seen in a study on the authorship of Shakespeare’s works, where multiple authorship was suggested
using machine learning techniques. Similarly, sentiment analysis allows for the identification of
emotional trends in literature, exemplified by analyses of Jane Austen’s novels and Pirandello’s War.
Additionally, topic modeling assists in summarizing large literary datasets, though it presents
limitations in fiction, as shown by analyses of the Gutenberg corpus. These digital approaches not
only provide new insights but also complement traditional methods, offering valuable quantitative
data to support qualitative interpretations. However, further research is needed to refine these
techniques and fully realize their potential in literary studies.