Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.19404218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>The unstructured nature of social media remains a challenge for extracting geographical information from texts. This paper discusses how a Generative Pretrained Transformer (GPT) can extract spatial information from social media texts. The preliminary results indicate that using toponym-based GPT solely to geoparse locational information yields vague, multiple-mentioned locations that cannot be geocoded. This research works toward the incorporation of topology to improve the accuracy of geoparsing and geocoding locations from social media texts.</p>