Incorporating Topology on GPT-Based Geoparsing Model for Finer Geocoding Locations from Social Media Texts

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Nurwatik, Nurwatik, Malleson, Nick, Oldroyd, Rachel, Comber, Alexis
Natura: Recurso digital
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901598615109632
author Nurwatik, Nurwatik
Malleson, Nick
Oldroyd, Rachel
Comber, Alexis
author_facet Nurwatik, Nurwatik
Malleson, Nick
Oldroyd, Rachel
Comber, Alexis
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>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19404218
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Incorporating Topology on GPT-Based Geoparsing Model for Finer Geocoding Locations from Social Media Texts
Nurwatik, Nurwatik
Malleson, Nick
Oldroyd, Rachel
Comber, Alexis
GPT, Geoparsing, Geocoding, Social Media
<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>
title Incorporating Topology on GPT-Based Geoparsing Model for Finer Geocoding Locations from Social Media Texts
topic GPT, Geoparsing, Geocoding, Social Media
url https://doi.org/10.5281/zenodo.19404218