Narrative networks help predict next day story developments in news
Investigating Forecasting Capabilities of Narrative Networks on Emerging Stories
Social and Information Networks
Summary
Stories in the news unfold by connecting different important elements, like people and events. The authors study if these connections and patterns can help predict what new links will appear the next day. They build networks based on news articles for three major real events and find that some standard methods can successfully guess the most likely new connections. The best method, called Preferential Attachment, works well especially for the most talked-about entities in the story.
What this means in practice
- •For news analytics teams: Predict how news story elements will connect the next day to inform story development monitoring.
- •For social media monitoring groups: Identify emerging relations in fast-moving events to better track event evolution and public discourse.
Authors
Ravi Teja Karumuri, Steven Corman, Huan Liu, Joshua Garland
Abstract
Networks have been used to model the interactions among the elements that underlie a narrative. In this paper, we investigate whether the structure of these networks can predict which links will emerge as a storyline evolves. We construct these networks from news articles using a Semantic Edge Parser (SEP) built on a Large Language Model (LLM), and evaluate the networks on three disparate real-world storylines, the 2022 Canadian Freedom Convoy, Hurricane Melissa (2025), and the 2025-26 Iranian protests. To test the narrative network's predictive capability, we construct a rolling window of the narrative and predict the emergent links between existing narrative elements on the day following the rolling window period. We identify candidate links with seven standard link predictors, including the Adamic-Adar index, Common Neighbors, and Preferential Attachment. Forecasting next-day links across the three storylines, we find Preferential Attachment to be the strongest standard link predictor, achieving a mean ROC-AUC of 0.76-0.79. It exceeds EdgeBank, a memorization baseline, by 11.3-14.5 points on every event. To summarize, narrative-network structure ranks next-day emergent relations above chance, though this advantage is concentrated among the most frequently mentioned, highly connected entities.