"This could save us months of work"-- Use Cases of AI and Automation Support in Investigative Journalism

2025-03-20

AI Summary

This paper addresses the low efficiency of repetitive data tasks—such as cross-site web scraping, content monitoring, summarization, and preliminary exploration—in investigative journalism. To tackle this, we propose a novel human-AI collaboration paradigm integrating large language models (LLMs) with programming-by-demonstration (PbD). Through an within-subject user study, in-depth interviews, and speculative design, we introduce PbD to investigative journalism workflows for the first time, establishing a journalist-centered task taxonomy (data acquisition and reporting) and identifying six high-value automation opportunities. Our prototype significantly lowers the barrier to cross-site data collection; we distill eight actionable guidelines for AI integration, validated and highly endorsed by frontline investigative journalists. Key contributions include: (1) pioneering an implementation pathway for LLM+PbD in journalistic practice; and (2) advancing a task-oriented, human-centered methodology for AI-augmented journalism.

Technology Category

• Humans and AI: Crowd Sourcing and Human Computation
• Application Domains: Humanities & Computational Social Science
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

As the capabilities of Large Language Models (LLMs) expand, more researchers are studying their adoption in newsrooms. However, much of the research focus remains broad and does not address the specific technical needs of investigative journalists. Therefore, this paper presents several applied use cases where automation and AI intersect with investigative journalism. We conducted a within-subjects user study with eight investigative journalists. In interviews, we elicited practical use cases using a speculative design approach by having journalists react to a prototype of a system that combines LLMs and Programming-by-Demonstration (PbD) to simplify data collection on numerous websites. Based on user reports, we classified the journalistic processes into data collecting and reporting. Participants indicated they utilize automation to handle repetitive tasks like content monitoring, web scraping, summarization, and preliminary data exploration. Following these insights, we provide guidelines on how investigative journalism can benefit from AI and automation.

Problem

• Addressing specific technical needs of investigative journalists using AI.
• Exploring automation in data collection and reporting for journalists.
• Providing guidelines on AI benefits in investigative journalism workflows.

Innovation

• Combines LLMs with Programming-by-Demonstration
• Simplifies data collection from multiple websites
• Automates repetitive tasks in journalism