DATAREEL: Automated Data-Driven Video Story Generation with Animations

TL;DR

DataReel introduces a benchmark and multi-agent framework for automated generation of animated data-driven video stories, addressing the challenge of coordinating visualization, narration, and animation.

Contribution

The paper presents a new benchmark dataset with 328 stories and a multi-agent approach for automated data video story generation, improving over baseline methods.

Findings

Multi-agent approach outperforms direct prompting baselines.

Experiments reveal challenges in coordinating animation, narration, and visual emphasis.

DataReel benchmark enables systematic evaluation of data-driven video storytelling models.

Abstract

Data videos are a powerful medium for visual data based storytelling, combining animated, chart-centric visualizations with synchronized narration. Widely used in journalism, education, and public communication, they help audiences understand complex data through clear and engaging visual explanations. Despite their growing impact, generating data-driven video stories remains challenging, as it requires careful coordination of visual encoding, temporal progression, and narration and substantial expertise in visualization design, animation, and video-editing tools. Recent advances in large language models offer new opportunities to automate this process; however, there is currently no benchmark for rigorously evaluating models on animated visualization-based video storytelling. To address this gap, we introduce DataReel, a benchmark for automated data-driven video story generation comprising 328 real-world stories. Each story pairs structured data, a chart visualization, and a narration transcript, enabling systematic evaluation of models' abilities to generate animated data video stories. We further propose a multi-agent framework that decomposes the task into planning, generation, and verification stages, mirroring key aspects of the human storytelling process. Experiments show that this multi-agent approach outperforms direct prompting baselines under both automatic and human evaluations, while revealing persistent challenges in coordinating animation, narration, and visual emphasis. We release DataReel at https://github.com/vis-nlp/DataReel.