Joshua Gorniak

Traditional accessibility methods like alternative text and data tables typically underrepresent data visualization’s full potential. Keyboard-based chart navigation has emerged as a potential solution, yet efficient data exploration remains challenging. We present VizAbility, a novel system that enriches chart content navigation with conversational interaction, enabling users to use natural language for querying visual data trends. VizAbility adapts to the user’s navigation context for improved response accuracy and facilitates verbal command-based chart navigation. Furthermore, it can address queries for contextual information, designed to address the needs of visually impaired users. We designed a large language model (LLM)-based pipeline to address these user queries, leveraging chart data & encoding, user context, and external web knowledge. We conducted both qualitative and quantitative studies to evaluate VizAbility’s multimodal approach. We discuss further opportunities based on the results, including improved benchmark testing, incorporation of vision models, and integration with visualization workflows.

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.