Loading [MathJax]/extensions/tex2jax.js

Multimodal Geolocation Estimation in News Documents

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandBeitrag in Buch/SammelwerkForschungPeer-Review

Autorschaft

  • Golsa Tahmasebzadeh
  • Eric Müller-Budack
  • Ralph Ewerth

Organisationseinheiten

Externe Organisationen

  • Technische Informationsbibliothek (TIB) Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek

Details

OriginalspracheEnglisch
Titel des SammelwerksEvent Analytics across Languages and Communities
Herausgeber (Verlag)Springer Nature
Seiten17-45
Seitenumfang29
ISBN (elektronisch)9783031644511
ISBN (Print)9783031644504
PublikationsstatusVeröffentlicht - 2025

Abstract

With the proliferation of news documents on the Internet, online news reading has become an important approach for information acquisition in people's daily lives. There has, however, been increasing concern with the growing infusion of misinformation. As a complement to news text, associated photos provide readers with additional information to facilitate their ability to find the information they need. To contextualise the vast amount of news that is published worldwide, the geographic content is crucial. On the other hand, the geographic content plays an important role in news recommendation to facilitate user desires. Existing approaches for geolocation estimation are primarily based on either text or photos as separate tasks. However, news photos can lack geographical cues, and text can include multiple locations. Therefore, it is challenging to recognise the focus location of the news story based on only one modality. We introduce novel datasets for multimodal geolocation estimation of news documents. We evaluate current methods on the benchmark datasets and suggest new methods for news geolocalisation using textual and visual content. In addition, we introduce a news retrieval system called GeoWINE based on the geographic content of news photos to emphasise the importance of geolocation estimation in the news domain.

ASJC Scopus Sachgebiete

Zitieren

Multimodal Geolocation Estimation in News Documents. / Tahmasebzadeh, Golsa; Müller-Budack, Eric; Ewerth, Ralph.
Event Analytics across Languages and Communities. Springer Nature, 2025. S. 17-45.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandBeitrag in Buch/SammelwerkForschungPeer-Review

Tahmasebzadeh, G, Müller-Budack, E & Ewerth, R 2025, Multimodal Geolocation Estimation in News Documents. in Event Analytics across Languages and Communities. Springer Nature, S. 17-45. https://doi.org/10.1007/978-3-031-64451-1_2
Tahmasebzadeh, G., Müller-Budack, E., & Ewerth, R. (2025). Multimodal Geolocation Estimation in News Documents. In Event Analytics across Languages and Communities (S. 17-45). Springer Nature. https://doi.org/10.1007/978-3-031-64451-1_2
Tahmasebzadeh G, Müller-Budack E, Ewerth R. Multimodal Geolocation Estimation in News Documents. in Event Analytics across Languages and Communities. Springer Nature. 2025. S. 17-45 Epub 2024 Jun 17. doi: 10.1007/978-3-031-64451-1_2
Tahmasebzadeh, Golsa ; Müller-Budack, Eric ; Ewerth, Ralph. / Multimodal Geolocation Estimation in News Documents. Event Analytics across Languages and Communities. Springer Nature, 2025. S. 17-45
Download
@inbook{45a58a5f6036413f9f6f0c07264fe841,
title = "Multimodal Geolocation Estimation in News Documents",
abstract = "With the proliferation of news documents on the Internet, online news reading has become an important approach for information acquisition in people's daily lives. There has, however, been increasing concern with the growing infusion of misinformation. As a complement to news text, associated photos provide readers with additional information to facilitate their ability to find the information they need. To contextualise the vast amount of news that is published worldwide, the geographic content is crucial. On the other hand, the geographic content plays an important role in news recommendation to facilitate user desires. Existing approaches for geolocation estimation are primarily based on either text or photos as separate tasks. However, news photos can lack geographical cues, and text can include multiple locations. Therefore, it is challenging to recognise the focus location of the news story based on only one modality. We introduce novel datasets for multimodal geolocation estimation of news documents. We evaluate current methods on the benchmark datasets and suggest new methods for news geolocalisation using textual and visual content. In addition, we introduce a news retrieval system called GeoWINE based on the geographic content of news photos to emphasise the importance of geolocation estimation in the news domain.",
author = "Golsa Tahmasebzadeh and Eric M{\"u}ller-Budack and Ralph Ewerth",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2025. All rights reserved.",
year = "2025",
doi = "10.1007/978-3-031-64451-1_2",
language = "English",
isbn = "9783031644504",
pages = "17--45",
booktitle = "Event Analytics across Languages and Communities",
publisher = "Springer Nature",
address = "United States",

}

Download

TY - CHAP

T1 - Multimodal Geolocation Estimation in News Documents

AU - Tahmasebzadeh, Golsa

AU - Müller-Budack, Eric

AU - Ewerth, Ralph

N1 - Publisher Copyright: © The Author(s) 2025. All rights reserved.

PY - 2025

Y1 - 2025

N2 - With the proliferation of news documents on the Internet, online news reading has become an important approach for information acquisition in people's daily lives. There has, however, been increasing concern with the growing infusion of misinformation. As a complement to news text, associated photos provide readers with additional information to facilitate their ability to find the information they need. To contextualise the vast amount of news that is published worldwide, the geographic content is crucial. On the other hand, the geographic content plays an important role in news recommendation to facilitate user desires. Existing approaches for geolocation estimation are primarily based on either text or photos as separate tasks. However, news photos can lack geographical cues, and text can include multiple locations. Therefore, it is challenging to recognise the focus location of the news story based on only one modality. We introduce novel datasets for multimodal geolocation estimation of news documents. We evaluate current methods on the benchmark datasets and suggest new methods for news geolocalisation using textual and visual content. In addition, we introduce a news retrieval system called GeoWINE based on the geographic content of news photos to emphasise the importance of geolocation estimation in the news domain.

AB - With the proliferation of news documents on the Internet, online news reading has become an important approach for information acquisition in people's daily lives. There has, however, been increasing concern with the growing infusion of misinformation. As a complement to news text, associated photos provide readers with additional information to facilitate their ability to find the information they need. To contextualise the vast amount of news that is published worldwide, the geographic content is crucial. On the other hand, the geographic content plays an important role in news recommendation to facilitate user desires. Existing approaches for geolocation estimation are primarily based on either text or photos as separate tasks. However, news photos can lack geographical cues, and text can include multiple locations. Therefore, it is challenging to recognise the focus location of the news story based on only one modality. We introduce novel datasets for multimodal geolocation estimation of news documents. We evaluate current methods on the benchmark datasets and suggest new methods for news geolocalisation using textual and visual content. In addition, we introduce a news retrieval system called GeoWINE based on the geographic content of news photos to emphasise the importance of geolocation estimation in the news domain.

UR - http://www.scopus.com/inward/record.url?scp=105002628736&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-64451-1_2

DO - 10.1007/978-3-031-64451-1_2

M3 - Contribution to book/anthology

AN - SCOPUS:105002628736

SN - 9783031644504

SP - 17

EP - 45

BT - Event Analytics across Languages and Communities

PB - Springer Nature

ER -