VizAbility: Multimodal Accessible Data Visualization with Keyboard Navigation and Conversational Interaction

Abstract

Data visualization serves as a crucial tool for communicating important information in our society. Yet, as visualizations grow more complex, they become less accessible to individuals with visual impairments. Traditional accessibility approaches like alternative text and data tables often fall short of capturing the full potential of data visualization. To bridge this gap, we introduce VizAbility, a novel multimodal accessible system that combines keyboard navigation with conventional interaction, enabling individuals with visual impairments to actively engage with and explore data visualizations. We built an LLM-based pipeline that classifies user queries and synthesizes underlying data, chart structure, user locality, and web-based information to answer the queries. Our preliminary evaluation using real-world questions from blind individuals demonstrates the significant potential of VizAbility.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.