Saved in:
Bibliographic Details
Main Authors: Hagar, Nick, Silver, Ethan, Spencer, Clare, Diakopoulos, Nicholas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.25491
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912615901429760
author Hagar, Nick
Silver, Ethan
Spencer, Clare
Diakopoulos, Nicholas
author_facet Hagar, Nick
Silver, Ethan
Spencer, Clare
Diakopoulos, Nicholas
contents Journalists face mounting challenges in monitoring ever-expanding digital information streams to identify newsworthy content. While traditional automation tools gather information at scale, they struggle with the editorial judgment needed to assess newsworthiness. This paper investigates whether large language models (LLMs) can serve as effective first-pass filters for journalistic monitoring. We develop a prompt-based approach encoding journalistic news values - timeliness, impact, controversy, and generalizability - into LLM instructions to extract and evaluate potential story leads. We validate our approach across multiple models against expert-annotated ground truth, then deploy a real-world monitoring pipeline that processes trade press articles daily. Our evaluation reveals strong performance in extracting relevant leads from source material ($F1=0.94$) and in coarse newsworthiness assessment ($\pm$1 accuracy up to 92%), but it consistently struggles with nuanced editorial judgments requiring beat expertise. The system proves most valuable as a hybrid tool combining automated monitoring with human review, successfully surfacing novel, high-value leads while filtering obvious noise. We conclude with practical recommendations for integrating LLM-powered monitoring into newsroom workflows that preserves editorial judgment while extending journalistic capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Assisted News Discovery in High-Volume Information Streams: A Case Study
Hagar, Nick
Silver, Ethan
Spencer, Clare
Diakopoulos, Nicholas
Human-Computer Interaction
Journalists face mounting challenges in monitoring ever-expanding digital information streams to identify newsworthy content. While traditional automation tools gather information at scale, they struggle with the editorial judgment needed to assess newsworthiness. This paper investigates whether large language models (LLMs) can serve as effective first-pass filters for journalistic monitoring. We develop a prompt-based approach encoding journalistic news values - timeliness, impact, controversy, and generalizability - into LLM instructions to extract and evaluate potential story leads. We validate our approach across multiple models against expert-annotated ground truth, then deploy a real-world monitoring pipeline that processes trade press articles daily. Our evaluation reveals strong performance in extracting relevant leads from source material ($F1=0.94$) and in coarse newsworthiness assessment ($\pm$1 accuracy up to 92%), but it consistently struggles with nuanced editorial judgments requiring beat expertise. The system proves most valuable as a hybrid tool combining automated monitoring with human review, successfully surfacing novel, high-value leads while filtering obvious noise. We conclude with practical recommendations for integrating LLM-powered monitoring into newsroom workflows that preserves editorial judgment while extending journalistic capacity.
title LLM-Assisted News Discovery in High-Volume Information Streams: A Case Study
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.25491