Movie Plot Analysis via Turning Point Identification

TL;DR

This paper introduces a method for identifying turning points in movie plots to analyze narrative structure, aiding in summarization and question answering, by using a neural network model trained on annotated screenplays.

Contribution

It presents a new dataset of annotated screenplays and plot synopses, and an end-to-end neural network model for turning point detection and projection onto scenes.

Findings

Model outperforms strong baselines in turning point identification.

Annotated dataset enables better understanding of narrative structure.

Facilitates long narrative processing for summarization and QA.

Abstract

According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments within a screenplay: they define the plot structure, determine its progression and segment the screenplay into thematic units (e.g., setup, complications, aftermath). We propose the task of turning point identification in movies as a means of analyzing their narrative structure. We argue that turning points and the segmentation they provide can facilitate processing long, complex narratives, such as screenplays, for summarization and question answering. We introduce a dataset consisting of screenplays and plot synopses annotated with turning points and present an end-to-end neural network model that identifies turning points in plot synopses and projects them onto scenes in screenplays. Our model outperforms strong baselines based on state-of-the-art sentence representations and the expected position of turning points.