Directed Character Networks of Western European Drama: A Large-Scale LLM-Based Exploratory Analysis

Character networks have become a standard tool for analyzing dramatic texts at scale, yet the dominant co-presence paradigm records only who shares the stage, not the directionality of speech that drives dramatic conflict and power. We address this limitation by employing Large Language Models (LLMs) to automatically identify the addressee for each utterance, thereby producing directed, weighted character networks that encode both the volume and directionality of speech. We illustrate the scalability of this approach through a large-scale cross-corpus analysis spanning 3327 plays across three Western European traditions (1931 French, 607 German, 789 English), examining diachronic trends in network density, character count, monologue frequency, and collective address from the 12th to the 21st century. Focused author-pair comparisons, such as Racine versus Corneille and Schiller versus Goethe, reveal distinct structural signatures that align with established literary-theoretical characterizations of these dramatists.