A Computational Approach to Walt Whitman's Stylistic Changes in Leaves of Grass

Abstract

This study analyzes Walt Whitman's stylistic changes in his phenomenal work Leaves of Grass from a computational perspective and relates findings to standard literary criticism on Whitman. The corpus consists of all 7 editions of Leaves of Grass, ranging from the earliest 1855 edition to the 1891-92 "deathbed" edition. Starting from counting word frequencies, the simplest stylometry technique, we find consistent shifts in word choice. Macro-etymological analysis reveals Whitman's increasing preference for words of specific origins, which is correlated to the increasing lexical complexity in Leaves of Grass. Principal component analysis, an unsupervised learning algorithm, reduces the dimensionality of tf-idf vectors to 2 dimensions, providing a straightforward view of stylistic changes. Finally, sentiment analysis shows the evolution of Whitman's emotional state throughout his writing career.