HCMar 8

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

arXiv:2603.07446v1Has Code
Predicted impact top 4% in HC · last 90 daysOriginality Highly original
AI Analysis

This system addresses a critical accessibility gap in geovisualization for screen-reader users, enabling them to interact with spatial information previously unavailable to them.

This paper introduces GeoVisA11y, an LLM-based question-answering system designed to make geovisualizations accessible to screen-reader users through natural language interaction. User studies with 12 screen-reader users demonstrated its effectiveness in bridging accessibility gaps, supporting map reading, analysis, interpretation, and navigation.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes