Stylometric analysis of characters in Shakespeare's plays.

This article investigates whether William Shakespeare employed distinct linguistic styles for male and female characters in his plays, reflecting recognized gender-based differences in language use. Using a set of nineteen stylistic markers—such as pronoun usage, determiners, prepositions, auxiliary verbs, and negations—previously validated on a tweet dataset from the CLEF-PAN corpora, the study analyzes 29 Shakespearean plays and finds statistically significant differences in the language attributed to male versus female characters. Two machine learning classifiers, logistic regression and random forest, achieved around 77–79% accuracy in automatically distinguishing male from female speech segments, supporting the conclusion that Shakespeare consciously differentiated gender styles. A comparative analysis with French playwright Philippe Quinault’s works showed no such gender-based stylistic distinctions, underscoring Shakespeare’s unique approach. The study also successfully classified major female characters (Juliet, Rosalind, Cleopatra) as female based on their linguistic patterns, further confirming the gender-specific style in Shakespeare’s writing.