Mapping News Narratives Using LLMs and Narrative-Structured Text Embeddings
This addresses the problem of computational narrative analysis for researchers and analysts in media studies or social sciences, offering a generalizable framework, though it is incremental as it builds on existing structuralist theory and LLM techniques.
The paper tackled the challenge of quantifying narratives in online news by introducing a numerical narrative representation based on Greimas' Actantial Model, using an LLM to extract actants and creating Narrative-Structured Text Embeddings; it demonstrated the method on 5000 news articles on the Israel-Palestine conflict, successfully distinguishing articles with similar topics but different narrative structures.
Given the profound impact of narratives across various societal levels, from personal identities to international politics, it is crucial to understand their distribution and development over time. This is particularly important in online spaces. On the Web, narratives can spread rapidly and intensify societal divides and conflicts. While many qualitative approaches exist, quantifying narratives remains a significant challenge. Computational narrative analysis lacks frameworks that are both comprehensive and generalizable. To address this gap, we introduce a numerical narrative representation grounded in structuralist linguistic theory. Chiefly, Greimas' Actantial Model represents a narrative through a constellation of six functional character roles. These so-called actants are genre-agnostic, making the model highly generalizable. We extract the actants using an open-source LLM and integrate them into a Narrative-Structured Text Embedding that captures both the semantics and narrative structure of a text. We demonstrate the analytical insights of the method on the example of 5000 full-text news articles from Al Jazeera and The Washington Post on the Israel-Palestine conflict. Our method successfully distinguishes articles that cover the same topics but differ in narrative structure.