Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
2026-06-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputation and LanguageComputers and SocietyHuman-Computer Interaction
AI summaryⓘ
The authors created Data Journalist Agent (Data2Story), a system that acts like a virtual newsroom with different roles working together to turn raw data into news stories. Their tool ensures every claim in the story links back to real data or sources and uses multimedia like interactive maps and audio to make the stories richer. They tested Data2Story by comparing its articles to real expert-written news and found it good at transparency and checking facts, though human journalists still do better with creative angles and design. The authors see their system as a helper for journalists to make reporting more evidence-based and trustworthy.
data journalismmulti-agent systemsevidence groundingmultimodal generationinteractive visualizationtransparencyverifiabilitynewsroom workflowdata storytelling
Authors
Kevin Qinghong Lin, Batu EI, Yuhong Shi, Pan Lu, Philip Torr, James Zou
Abstract
Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team weeks: hunting for context, running statistics, choosing an angle, and designing visuals. Recent agents handle individual steps well: data-science agents close the analysis loop, while design agents synthesize beautiful websites. But can an agent serve as a data journalist end to end? We introduce Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom. Data2Story contributes two innovations. (i) Claims are evidence-grounded: an Inspector links every number, angle, and asset back to data, code, or an external reference. (ii) Articles are multimodally generative: rather than defaulting to plain text and static charts, Data2Story reasons about what readers will want to see, then deploys multimodal tools, such as interactive maps for geography and audio for music. We evaluate Data2Story on 18 articles, each paired with the originally published expert piece, along four axes: (a) human-agent angle coverage; (b) rubric evaluation with 53 participants across five dimensions; (c) computer-use agents as judges, a cost-saving proxy for how readers navigate interactive articles; and (d) verifiability, where a coding verifier re-executes statements against the data and checks claims against references. Data2Story produces competitive, evidence-traceable multimedia stories, with particular strength in transparency and auditability. Human articles retain an edge in editorial angle, creative design, and presentation. We position Data2Story as a collaborator for journalists, enabling more evidence-based, transparent, and verifiable reporting. Code and demos are available at https://data2story.github.io.