NewsVis: GenAI-based Visual Storytelling for Corporate Financial News

Jia Bu, Mingwei Jiang, Shuqi Liu, Tong Lyu, Lumeng Wu, Shiqi Jiang, Boyuan Huangfu, Changbo Wang, Chenhui LiIEEE TVCG 2026 · OpenReview

Abstract

Corporate financial news is pivotal for market decisions, but often overwhelms general audiences. While data videos effectively bridge this comprehension gap, their production remains a bottleneck for journalists. We present NewsVis, an authoring tool powered by Generative Artificial Intelligence (GenAI) that automates the transformation of unstructured narratives and raw financial datasets into professional data videos. Unlike generic models, our pipeline ensures factual accuracy through a domain-specific taxonomy of financial attributes and optimizes visual information presentation via a multimodal layout algorithm. Additionally, a human-in-the-loop interface empowers journalists to audit and calibrate generative outputs. Comprehensive quantitative and qualitative evaluations demonstrate that NewsVis significantly reduces production barriers while enhancing information accessibility for viewers.
BibTeX
@article{bu2026newsvis,
  author = {Jia Bu and Mingwei Jiang and Shuqi Liu and Tong Lyu and Lumeng Wu and Shiqi Jiang and Boyuan Huangfu and Changbo Wang and Chenhui Li},
  title = {{NewsVis: GenAI-based Visual Storytelling for Corporate Financial News}},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  year = {2026},
  url = {https://openreview.net/forum?id=h722YwHVN9},
}

Loading related content...

Figure