Saved in:
Bibliographic Details
Main Authors: Madureira, Brielen, de Brito, Mariana Madruga, Niekler, Andreas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.03414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918482944196608
author Madureira, Brielen
de Brito, Mariana Madruga
Niekler, Andreas
author_facet Madureira, Brielen
de Brito, Mariana Madruga
Niekler, Andreas
contents Determining the geolocation of extreme climate events and disasters in texts is a common problem in climate impact and adaptation research. Named-entity recognition (NER) tools are typically used to identify a pool of toponyms that serve as candidate event locations. In this study, we conduct a comparative analysis of three off-the-shelf NER tools, namely Flair, Spacy and Stanza. We describe and quantify differences between their outputs for German news articles and evaluate them extrinsically based on three methods to determine the country where events took place. We show how their contrasts are propagated into downstream tasks and can yield distinct decisions about a document's geographical focus, which, in turn, can impact conclusions about countries' prominence in German media.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03414
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German
Madureira, Brielen
de Brito, Mariana Madruga
Niekler, Andreas
Computation and Language
Determining the geolocation of extreme climate events and disasters in texts is a common problem in climate impact and adaptation research. Named-entity recognition (NER) tools are typically used to identify a pool of toponyms that serve as candidate event locations. In this study, we conduct a comparative analysis of three off-the-shelf NER tools, namely Flair, Spacy and Stanza. We describe and quantify differences between their outputs for German news articles and evaluate them extrinsically based on three methods to determine the country where events took place. We show how their contrasts are propagated into downstream tasks and can yield distinct decisions about a document's geographical focus, which, in turn, can impact conclusions about countries' prominence in German media.
title Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German
topic Computation and Language
url https://arxiv.org/abs/2605.03414