Reviving Static Charts into Live Charts

Abstract

Data charts are prevalent across various fields due to their efficacy in conveying complex data relationships. However, static charts may sometimes struggle to engage readers and efficiently present intricate information, potentially resulting in limited understanding. We introduce "Live Charts," a new format of presentation that decomposes complex information within a chart and explains the information pieces sequentially through rich animations and accompanying audio narration. We propose an automated approach to revive static charts into Live Charts. Our method integrates GNN-based techniques to analyze the chart components and extract data from charts. Then we adopt large natural language models to generate appropriate animated visuals along with a voice-over to produce Live Charts from static ones. We conducted a thorough evaluation of our approach, which involved the model performance, use cases, a crowd-sourced user study, and expert interviews. The results demonstrate Live Charts offer a multi-sensory experience where readers can follow the information and understand the data insights better. We analyze the benefits and drawbacks of Live Charts over static charts as a new information consumption experience.

Accepted by IEEE TVCG

References in corpus (17)

• Calliope: Automatic Visual Data Story Generation from a Spreadsheet
• FigureQA: An Annotated Figure Dataset for Visual Reasoning
• ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language
• Eight Things to Know about Large Language Models
• OpenAGI: When LLM Meets Domain Experts
• Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data
• Searching the Visual Style and Structure of D3 Visualizations
• Chart-Text: A Fully Automated Chart Image Descriptor
• Narvis: Authoring Narrative Slideshows for Introducing Data Visualization Designs
• Notable: On-the-fly Assistant for Data Storytelling in Computational Notebooks
• Structure-aware Visualization Retrieval
• a survey on GPT-3
• Revealing the Semantics of Data Wrangling Scripts With COMANTICS
• LEAF-QA: Locate, Encode & Attend for Figure Question Answering
• Recognizing Vector Graphics without Rasterization
• VAID: Indexing View Designs in Visual Analytics System
• Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration

Cited by in corpus (6)

• ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language
• Narrative Player: Reviving Data Narratives with Visuals
• VAID: Indexing View Designs in Visual Analytics System
• InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions
• Plume: Scaffolding Text Composition in Dashboards
• ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs