On the role of images for analyzing claims in social media

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

  • Gullal S. Cheema
  • Sherzod Hakimov
  • Eric Müller-Budack
  • Ralph Ewerth

Externe Organisationen

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

Details

OriginalspracheEnglisch
Titel des SammelwerksCross-lingual Event-centric Open Analytics
UntertitelProceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021)
Seiten32-46
Seitenumfang15
PublikationsstatusVeröffentlicht - 2021
Extern publiziertJa
Veranstaltung2nd International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2021 - Virtual, Ljubljana, Slowenien
Dauer: 12 Apr. 2021 → …

Publikationsreihe

NameCEUR Workshop Proceedings
Herausgeber (Verlag)CEUR WS
Band2829
ISSN (Print)1613-0073

Abstract

Fake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.

ASJC Scopus Sachgebiete

Zitieren

On the role of images for analyzing claims in social media. / Cheema, Gullal S.; Hakimov, Sherzod; Müller-Budack, Eric et al.
Cross-lingual Event-centric Open Analytics: Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021). 2021. S. 32-46 (CEUR Workshop Proceedings; Band 2829).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Cheema, GS, Hakimov, S, Müller-Budack, E & Ewerth, R 2021, On the role of images for analyzing claims in social media. in Cross-lingual Event-centric Open Analytics: Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021). CEUR Workshop Proceedings, Bd. 2829, S. 32-46, 2nd International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2021, Virtual, Ljubljana, Slowenien, 12 Apr. 2021. https://doi.org/10.48550/arXiv.2103.09602
Cheema, G. S., Hakimov, S., Müller-Budack, E., & Ewerth, R. (2021). On the role of images for analyzing claims in social media. In Cross-lingual Event-centric Open Analytics: Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021) (S. 32-46). (CEUR Workshop Proceedings; Band 2829). https://doi.org/10.48550/arXiv.2103.09602
Cheema GS, Hakimov S, Müller-Budack E, Ewerth R. On the role of images for analyzing claims in social media. in Cross-lingual Event-centric Open Analytics: Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021). 2021. S. 32-46. (CEUR Workshop Proceedings). doi: 10.48550/arXiv.2103.09602
Cheema, Gullal S. ; Hakimov, Sherzod ; Müller-Budack, Eric et al. / On the role of images for analyzing claims in social media. Cross-lingual Event-centric Open Analytics: Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 30th The Web Conference (WWW 2021). 2021. S. 32-46 (CEUR Workshop Proceedings).
Download
@inproceedings{8363910d5c4f49aab110943626558d39,
title = "On the role of images for analyzing claims in social media",
abstract = "Fake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.",
keywords = "5G, Claim detection, Computer vision, Conspiracy detection, COVID-19, Fake news detection, Multilingual NLP, Multimodal analysis, Transformers, Twitter",
author = "Cheema, {Gullal S.} and Sherzod Hakimov and Eric M{\"u}ller-Budack and Ralph Ewerth",
note = "Funding information: This work was funded by European Union{\textquoteright}s Horizon 2020 research and innovation programme under the Marie Sk lodowska-Curie grant agreement no 812997. This work was funded by European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no 812997. ; 2nd International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2021 ; Conference date: 12-04-2021",
year = "2021",
doi = "10.48550/arXiv.2103.09602",
language = "English",
series = "CEUR Workshop Proceedings",
publisher = "CEUR WS",
pages = "32--46",
booktitle = "Cross-lingual Event-centric Open Analytics",

}

Download

TY - GEN

T1 - On the role of images for analyzing claims in social media

AU - Cheema, Gullal S.

AU - Hakimov, Sherzod

AU - Müller-Budack, Eric

AU - Ewerth, Ralph

N1 - Funding information: This work was funded by European Union’s Horizon 2020 research and innovation programme under the Marie Sk lodowska-Curie grant agreement no 812997. This work was funded by European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no 812997.

PY - 2021

Y1 - 2021

N2 - Fake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.

AB - Fake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.

KW - 5G

KW - Claim detection

KW - Computer vision

KW - Conspiracy detection

KW - COVID-19

KW - Fake news detection

KW - Multilingual NLP

KW - Multimodal analysis

KW - Transformers

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85103154894&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2103.09602

DO - 10.48550/arXiv.2103.09602

M3 - Conference contribution

AN - SCOPUS:85103154894

T3 - CEUR Workshop Proceedings

SP - 32

EP - 46

BT - Cross-lingual Event-centric Open Analytics

T2 - 2nd International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2021

Y2 - 12 April 2021

ER -