System compares how news outlets report the same events differently
Same Story, Different Lens: A Multi-Agent System for Cross-Outlet News Framing Analysis
Artificial Intelligence
Summary
News outlets often tell the same story in different ways, focusing on some parts and leaving out others. The authors introduce a system that collects articles about the same events from 17 sources and analyzes how each outlet frames the news. It looks for things like sentiment, political bias, language choices, and whether news is presented more as fact or opinion. The system uses multiple agents to break down the articles and then summarizes the differences. This tool helps reveal how the same event is reported differently across news sources.
What this means in practice
- •For media monitoring teams: Generate structured reports comparing coverage bias and framing across multiple news outlets for the same event.
- •For public relations teams: Assess how different news sources portray a client or event to inform messaging strategies.
Authors
Affan Yasin, Yueqi Lyu, Rubia Fatima, Weinchen Zhong, Keyi Li
Abstract
News outlets covering the same event differ in what they emphasize and omit. \textit{Same Story, Different Lens} is an experimental research prototype for comparing these choices. It collects world and politics coverage from 17 outlets, groups reports about the same event, and produces structured analyses of sentiment, political lean, framing, loaded language, possible omissions, and model-estimated proportions of factual claims and opinion. Loaded-language entries include quotations and neutral rewordings. Three model roles (agents) handle article analysis, assessment of source support, and cross-outlet briefing generation. Analyses are stored in a JSONL archive. The evaluation compares outlet-level lean estimates with approximate, predefined reference ratings and summarizes the Critic's model-assigned grounding scores. These measures provide preliminary diagnostics. A grounding score reflects the model's assessment of support in the supplied text and does not establish factual accuracy or constitute independent verification.