GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912951879860224 |
|---|---|
| author | Li, Chu Pang, Rock Yuren Chheda-Kothary, Arnavi Sharif, Ather Assalif, Henok Heer, Jeffrey Froehlich, Jon E. |
| author_facet | Li, Chu Pang, Rock Yuren Chheda-Kothary, Arnavi Sharif, Ather Assalif, Henok Heer, Jeffrey Froehlich, Jon E. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07446 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users Li, Chu Pang, Rock Yuren Chheda-Kothary, Arnavi Sharif, Ather Assalif, Henok Heer, Jeffrey Froehlich, Jon E. Human-Computer Interaction 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. |
| title | GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2603.07446 |