Portrayal: Leveraging NLP and Visualization for Analyzing Fictional Characters

TL;DR

Portrayal is an interactive system combining NLP and visualization to assist writers and scholars in analyzing and creating complex characters in stories, reducing manual effort and enhancing interpretative insights.

Contribution

The paper introduces Portrayal, a novel system that integrates NLP and visualization for character analysis in fiction, streamlining literary analysis and creative writing tasks.

Findings

Helped writers revise drafts and develop dynamic characters.

Enabled scholars to analyze characters without manual annotation.

Supported evidence-based literary argumentation.

Abstract

Many creative writing tasks (e.g., fiction writing) require authors to write complex narrative components (e.g., characterization, events, dialogue) over the course of a long story. Similarly, literary scholars need to manually annotate and interpret texts to understand such abstract components. In this paper, we explore how Natural Language Processing (NLP) and interactive visualization can help writers and scholars in such scenarios. To this end, we present Portrayal, an interactive visualization system for analyzing characters in a story. Portrayal extracts natural language indicators from a text to capture the characterization process and then visualizes the indicators in an interactive interface. We evaluated the system with 12 creative writers and scholars in a one-week-long qualitative study. Our findings suggest Portrayal helped writers revise their drafts and create dynamic characters and scenes. It helped scholars analyze characters without the need for any manual annotation, and design literary arguments with concrete evidence.