Composing Data Stories with Meta Relations

2025-01-07

AI Summary

Existing AI-powered data storytelling tools rely solely on data-layer relationships, resulting in rigid, homogeneous, and logically constrained narratives. To address this, we introduce—first in the literature—the concept of *meta-relations*: high-level, semantically rich abstractions that encode domain knowledge and narrative intent, enabling flexible orchestration of analytical insights. We integrate meta-relations into the data storytelling pipeline via a human-AI co-creation framework, supporting proactive suggestion and dynamic application of meta-relations during both analytical exploration and narrative structuring phases. We implement this approach in Remex, an interactive prototype tool, and conduct empirical validation through user studies, qualitative analysis, and workflow modeling. Results demonstrate that meta-relations significantly enhance narrative expressiveness, logical coherence, and contextual adaptability; reveal three recurrent human-AI collaboration patterns; and yield reusable design principles and practical guidelines—establishing a novel paradigm for stylistically diverse, knowledge-augmented AI storytelling systems.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• 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: Bridging structured and unstructured data
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

To facilitate the creation of compelling and engaging data stories, AI-powered tools have been introduced to automate the three stages in the workflow: analyzing data, organizing findings, and creating visuals. However, these tools rely on data-level information to derive inflexible relations between findings. Therefore, they often create one-size-fits-all data stories. Differently, our formative study reveals that humans heavily rely on meta relations between these findings from diverse domain knowledge and narrative intent, going beyond datasets, to compose their findings into stylized data stories. Such a gap indicates the importance of introducing meta relations to elevate AI-created stories to a satisfactory level. Though necessary, it is still unclear where and how AI should be involved in working with humans on meta relations. To answer the question, we conducted an exploratory user study with Remex, an AI-powered data storytelling tool that suggests meta relations in the analysis stage and applies meta relations for data story organization. The user study reveals various findings about introducing AI for meta relations into the storytelling workflow, such as the benefit of considering meta relations and their diverse expected usage scenarios. Finally, the paper concludes with lessons and suggestions about applying meta relations to compose data stories to hopefully inspire future research.

Problem

• Artificial Intelligence
• Data Storytelling
• Human-like Narration

Innovation

• Remex
• Data Storytelling
• Artificial Intelligence