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

2025-03-04

Proceedings of the 17th International Conference on Agents and Artificial Intelligence

AI Summary

This paper addresses the low efficiency and modeling difficulty inherent in manual analysis of television drama narrative arcs. We propose the first multi-agent collaborative framework specifically designed for analyzing episodic narrative structure. Methodologically, we construct a dual-modal knowledge storage system integrating relational databases with semantic vector embeddings; design a taxonomy of three narrative arc types—anthology, soap, and genre-specific; and develop an interactive visualization interface supporting human verification and interpretive feedback. Our contributions include: (1) establishing a closed-loop analytical paradigm that integrates automated extraction with humanistic interpretation; (2) validating cross-media narrative analysis feasibility on Season 1 of *Grey’s Anatomy*; and (3) revealing the limitations of pure text-based input in capturing multiply layered and implicit dynamic arcs—thereby offering a novel methodology for film/TV computing and digital humanities research. (149 words)

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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.

Problem

• Extracts and analyzes narrative arcs in TV series
• Identifies Anthology, Soap, and Genre-Specific arcs
• Combines computational and human expertise for narrative analysis

Innovation

• Multi-agent system for narrative arc extraction
• Relational and semantic databases for data storage
• Graphical interface for human refinement and visualization