GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users

TL;DR

GeoVisA11y is an AI-powered system that enables screen-reader users to interact with and understand geovisualizations through natural language queries, improving accessibility and usability.

Contribution

The paper introduces an open-source geovisualization system that leverages large language models to support accessible spatial data interaction for visually impaired users.

Findings

Effective in bridging accessibility gaps for screen-reader users.

Revealed distinct interaction patterns between users with and without visual impairments.

Provided a dataset of geospatial queries to guide future research.

Abstract

Geovisualizations are powerful tools for communicating spatial information, but are inaccessible to screen-reader users. To address this limitation, we present GeoVisA11y, an LLM-based question-answering system that makes geovisualizations accessible through natural language interaction. The system supports map reading, analysis, interpretation and navigation by handling analytical, geospatial, visual and contextual queries. Through user studies with 12 screen-reader users and sighted participants, we demonstrate that GeoVisA11y effectively bridges accessibility gaps while revealing distinct interaction patterns between user groups. We contribute: (1) an open-source, accessible geovisualization system, (2) empirical findings on query and navigation differences, and (3) a dataset of geospatial queries to inform future research on accessible data visualization.