MARCUS: An Event-Centric NLP Pipeline that generates Character Arcs from Narratives

TL;DR

MARCUS is an NLP pipeline that automatically extracts and visualizes character arcs from narratives by analyzing events, characters, emotions, and sentiments, aiding literary analysis and understanding.

Contribution

This work introduces MARCUS, a novel NLP pipeline that computationally generates character arcs from narratives, combining event extraction and relation modeling.

Findings

Successfully generated character arcs for Harry Potter and Lord of the Rings.

Demonstrated the pipeline's ability to track character development over narratives.

Identified challenges and potential applications for the approach.

Abstract

Character arcs are important theoretical devices employed in literary studies to understand character journeys, identify tropes across literary genres, and establish similarities between narratives. This work addresses the novel task of computationally generating event-centric, relation-based character arcs from narratives. Providing a quantitative representation for arcs brings tangibility to a theoretical concept and paves the way for subsequent applications. We present MARCUS (Modelling Arcs for Understanding Stories), an NLP pipeline that extracts events, participant characters, implied emotion, and sentiment to model inter-character relations. MARCUS tracks and aggregates these relations across the narrative to generate character arcs as graphical plots. We generate character arcs from two extended fantasy series, Harry Potter and Lord of the Rings. We evaluate our approach before outlining existing challenges, suggesting applications of our pipeline, and discussing future work.