Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series

Roberto Balestri, Guglielmo Pescatore

TL;DR

The paper addresses the challenge of extracting and analyzing narrative arcs in serialized TV series by proposing a multi-agent system that processes episode plots to identify Anthology, Soap, and Genre-Specific arcs. Arcs and their episodic progressions are stored in relational and vector databases, with a graphical interface enabling human refinement to bridge automation and interpretation. The approach demonstrates strong performance in identifying Anthology arcs and character entities, while highlighting limitations due to reliance on paratexts and issues with overlapping arcs. The work showcases a practical human-in-the-loop framework with potential applicability to serialized written narratives and outlines future directions toward multimodal inputs and broader genre testing.

Abstract

Serialized TV shows are built on complex storylines that can be hard to track and evolve in ways that defy straightforward analysis. This paper introduces a multi-agent system designed to extract and analyze these narrative arcs. Tested on the first season of Grey's Anatomy (ABC 2005-), the system identifies three types of arcs: Anthology (self-contained), Soap (relationship-focused), and Genre-Specific (strictly related to the series' genre). Episodic progressions of these arcs are stored in both relational and semantic (vectorial) databases, enabling structured analysis and comparison. To bridge the gap between automation and critical interpretation, the system is paired with a graphical interface that allows for human refinement using tools to enhance and visualize the data. The system performed strongly in identifying Anthology Arcs and character entities, but its reliance on textual paratexts (such as episode summaries) revealed limitations in recognizing overlapping arcs and subtler dynamics. This approach highlights the potential of combining computational and human expertise in narrative analysis. Beyond television, it offers promise for serialized written formats, where the narrative resides entirely in the text. Future work will explore the integration of multimodal inputs, such as dialogue and visuals, and expand testing across a wider range of genres to refine the system further.

Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series

TL;DR

The paper addresses the challenge of extracting and analyzing narrative arcs in serialized TV series by proposing a multi-agent system that processes episode plots to identify Anthology, Soap, and Genre-Specific arcs. Arcs and their episodic progressions are stored in relational and vector databases, with a graphical interface enabling human refinement to bridge automation and interpretation. The approach demonstrates strong performance in identifying Anthology arcs and character entities, while highlighting limitations due to reliance on paratexts and issues with overlapping arcs. The work showcases a practical human-in-the-loop framework with potential applicability to serialized written narratives and outlines future directions toward multimodal inputs and broader genre testing.

Abstract

Serialized TV shows are built on complex storylines that can be hard to track and evolve in ways that defy straightforward analysis. This paper introduces a multi-agent system designed to extract and analyze these narrative arcs. Tested on the first season of Grey's Anatomy (ABC 2005-), the system identifies three types of arcs: Anthology (self-contained), Soap (relationship-focused), and Genre-Specific (strictly related to the series' genre). Episodic progressions of these arcs are stored in both relational and semantic (vectorial) databases, enabling structured analysis and comparison. To bridge the gap between automation and critical interpretation, the system is paired with a graphical interface that allows for human refinement using tools to enhance and visualize the data. The system performed strongly in identifying Anthology Arcs and character entities, but its reliance on textual paratexts (such as episode summaries) revealed limitations in recognizing overlapping arcs and subtler dynamics. This approach highlights the potential of combining computational and human expertise in narrative analysis. Beyond television, it offers promise for serialized written formats, where the narrative resides entirely in the text. Future work will explore the integration of multimodal inputs, such as dialogue and visuals, and expand testing across a wider range of genres to refine the system further.

Paper Structure

This paper contains 39 sections, 5 figures.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORKS
  3. Advances in Computational Narrative Analysis
  4. Temporal and Structural Analysis of Narratives
  5. Multi-Agent Systems in Narrative Understanding
  6. Narrative Arcs (Plotlines)
  7. MODELING NARRATIVE ARCS FOR STORING
  8. TECHNICAL DETAILS
  9. MATERIAL COLLECTION AND PREPROCESSING
  10. Episodes' Plots Gathering
  11. Data Cleaning and Simplification
  12. Character Entity Normalization
  13. Season Plot Generation
  14. THE MULTI-AGENT SYSTEM FOR ARC EXTRACTION
  15. Workflow Design
  16. ...and 24 more sections

Figures (5)

  • Figure 1: Narrative Arc Extraction Process
  • Figure 2: The main view of the graphical interface.
  • Figure 3: Form to add a new arc.
  • Figure 4: 3D PCA visualizer for clustering arcs based on semantic similarity.
  • Figure 5: Jaccard Index indicating potential duplicated characters. In this example, the suggestion is a false positive.