Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models

TL;DR

This paper introduces a hybrid method combining dynamic topic models and large language models to detect and interpret narrative shifts over time in media, balancing computational efficiency with narrative understanding.

Contribution

It presents a novel pipeline that integrates topic modeling and LLMs to identify and analyze narrative changes in large corpora, addressing computational challenges.

Findings

LLMs can efficiently detect narrative shifts at specific points.

The method distinguishes between content and narrative shifts.

The approach is applied to WSJ articles from 2009-2023.

Abstract

With rapidly evolving media narratives, it has become increasingly critical to not just extract narratives from a given corpus but rather investigate, how they develop over time. While popular narrative extraction methods such as Large Language Models do well in capturing typical narrative elements or even the complex structure of a narrative, applying them to an entire corpus comes with obstacles, such as a high financial or computational cost. We propose a combination of the language understanding capabilities of Large Language Models with the large scale applicability of topic models to dynamically model narrative shifts across time using the Narrative Policy Framework. We apply a topic model and a corresponding change point detection method to find changes that concern a specific topic of interest. Using this model, we filter our corpus for documents that are particularly representative of that change and feed them into a Large Language Model that interprets the change that happened in an automated fashion and distinguishes between content and narrative shifts. We employ our pipeline on a corpus of The Wall Street Journal news paper articles from 2009 to 2023. Our findings indicate that a Large Language Model can efficiently extract a narrative shift if one exists at a given point in time, but does not perform as well when having to decide whether a shift in content or a narrative shift took place.