MM-Claims: A Dataset for Multimodal Claim Detection in Social Media

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Autoren

  • Gullal S. Cheema
  • Sherzod Hakimov
  • Abdul Sittar
  • Eric Muller-Budack
  • Christian Otto
  • Ralph Ewerth

Organisationseinheiten

Externe Organisationen

  • Technische Informationsbibliothek (TIB) Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek
  • Institut "Jožef Stefan" (IJS)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksFindings of the Association for Computational Linguistics
UntertitelNAACL 2022 - Findings
Seiten962-979
Seitenumfang18
ISBN (elektronisch)9781955917766
PublikationsstatusVeröffentlicht - Juli 2022
Veranstaltung2022 Findings of the Association for Computational Linguistics: NAACL 2022 - Seattle, USA / Vereinigte Staaten
Dauer: 10 Juli 2022 → 15 Juli 2022

Publikationsreihe

NameFindings of the Association for Computational Linguistics: NAACL 2022 - Findings

Abstract

In recent years, the problem of misinformation on the web has become widespread across languages, countries, and various social media platforms. Although there has been much work on automated fake news detection, the role of images and their variety are not well explored. In this paper, we investigate the roles of image and text at an earlier stage of the fake news detection pipeline, called claim detection. For this purpose, we introduce a novel dataset, MM-Claims, which consists of tweets and corresponding images over three topics: COVID- 19, Climate Change and broadly Technology. The dataset contains roughly 86 000 tweets, out of which 3400 are labeled manually by multiple annotators for the training and evaluation of multimodal models. We describe the dataset in detail, evaluate strong unimodal and multimodal baselines, and analyze the potential and drawbacks of current models.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

MM-Claims: A Dataset for Multimodal Claim Detection in Social Media. / Cheema, Gullal S.; Hakimov, Sherzod; Sittar, Abdul et al.
Findings of the Association for Computational Linguistics: NAACL 2022 - Findings. 2022. S. 962-979 (Findings of the Association for Computational Linguistics: NAACL 2022 - Findings).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Cheema, GS, Hakimov, S, Sittar, A, Muller-Budack, E, Otto, C & Ewerth, R 2022, MM-Claims: A Dataset for Multimodal Claim Detection in Social Media. in Findings of the Association for Computational Linguistics: NAACL 2022 - Findings. Findings of the Association for Computational Linguistics: NAACL 2022 - Findings, S. 962-979, 2022 Findings of the Association for Computational Linguistics: NAACL 2022, Seattle, USA / Vereinigte Staaten, 10 Juli 2022. https://doi.org/10.48550/arXiv.2205.01989, https://doi.org/10.18653/v1/2022.findings-naacl.72
Cheema, G. S., Hakimov, S., Sittar, A., Muller-Budack, E., Otto, C., & Ewerth, R. (2022). MM-Claims: A Dataset for Multimodal Claim Detection in Social Media. In Findings of the Association for Computational Linguistics: NAACL 2022 - Findings (S. 962-979). (Findings of the Association for Computational Linguistics: NAACL 2022 - Findings). https://doi.org/10.48550/arXiv.2205.01989, https://doi.org/10.18653/v1/2022.findings-naacl.72
Cheema GS, Hakimov S, Sittar A, Muller-Budack E, Otto C, Ewerth R. MM-Claims: A Dataset for Multimodal Claim Detection in Social Media. in Findings of the Association for Computational Linguistics: NAACL 2022 - Findings. 2022. S. 962-979. (Findings of the Association for Computational Linguistics: NAACL 2022 - Findings). doi: 10.48550/arXiv.2205.01989, 10.18653/v1/2022.findings-naacl.72
Cheema, Gullal S. ; Hakimov, Sherzod ; Sittar, Abdul et al. / MM-Claims : A Dataset for Multimodal Claim Detection in Social Media. Findings of the Association for Computational Linguistics: NAACL 2022 - Findings. 2022. S. 962-979 (Findings of the Association for Computational Linguistics: NAACL 2022 - Findings).
Download
@inproceedings{b1131824aedc40ea88138aa4527a7b97,
title = "MM-Claims: A Dataset for Multimodal Claim Detection in Social Media",
abstract = "In recent years, the problem of misinformation on the web has become widespread across languages, countries, and various social media platforms. Although there has been much work on automated fake news detection, the role of images and their variety are not well explored. In this paper, we investigate the roles of image and text at an earlier stage of the fake news detection pipeline, called claim detection. For this purpose, we introduce a novel dataset, MM-Claims, which consists of tweets and corresponding images over three topics: COVID- 19, Climate Change and broadly Technology. The dataset contains roughly 86 000 tweets, out of which 3400 are labeled manually by multiple annotators for the training and evaluation of multimodal models. We describe the dataset in detail, evaluate strong unimodal and multimodal baselines, and analyze the potential and drawbacks of current models.",
author = "Cheema, {Gullal S.} and Sherzod Hakimov and Abdul Sittar and Eric Muller-Budack and Christian Otto 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{\l}odowska-Curie grant agreement no 812997 (CLEOPATRA project), and by the German Federal Ministry of Education and Research (BMBF, FakeNarratives project, no. 16KIS1517). ; 2022 Findings of the Association for Computational Linguistics: NAACL 2022 ; Conference date: 10-07-2022 Through 15-07-2022",
year = "2022",
month = jul,
doi = "10.48550/arXiv.2205.01989",
language = "English",
series = "Findings of the Association for Computational Linguistics: NAACL 2022 - Findings",
pages = "962--979",
booktitle = "Findings of the Association for Computational Linguistics",

}

Download

TY - GEN

T1 - MM-Claims

T2 - 2022 Findings of the Association for Computational Linguistics: NAACL 2022

AU - Cheema, Gullal S.

AU - Hakimov, Sherzod

AU - Sittar, Abdul

AU - Muller-Budack, Eric

AU - Otto, Christian

AU - Ewerth, Ralph

N1 - Funding Information: This work was funded by European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no 812997 (CLEOPATRA project), and by the German Federal Ministry of Education and Research (BMBF, FakeNarratives project, no. 16KIS1517).

PY - 2022/7

Y1 - 2022/7

N2 - In recent years, the problem of misinformation on the web has become widespread across languages, countries, and various social media platforms. Although there has been much work on automated fake news detection, the role of images and their variety are not well explored. In this paper, we investigate the roles of image and text at an earlier stage of the fake news detection pipeline, called claim detection. For this purpose, we introduce a novel dataset, MM-Claims, which consists of tweets and corresponding images over three topics: COVID- 19, Climate Change and broadly Technology. The dataset contains roughly 86 000 tweets, out of which 3400 are labeled manually by multiple annotators for the training and evaluation of multimodal models. We describe the dataset in detail, evaluate strong unimodal and multimodal baselines, and analyze the potential and drawbacks of current models.

AB - In recent years, the problem of misinformation on the web has become widespread across languages, countries, and various social media platforms. Although there has been much work on automated fake news detection, the role of images and their variety are not well explored. In this paper, we investigate the roles of image and text at an earlier stage of the fake news detection pipeline, called claim detection. For this purpose, we introduce a novel dataset, MM-Claims, which consists of tweets and corresponding images over three topics: COVID- 19, Climate Change and broadly Technology. The dataset contains roughly 86 000 tweets, out of which 3400 are labeled manually by multiple annotators for the training and evaluation of multimodal models. We describe the dataset in detail, evaluate strong unimodal and multimodal baselines, and analyze the potential and drawbacks of current models.

UR - http://www.scopus.com/inward/record.url?scp=85137337054&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2205.01989

DO - 10.48550/arXiv.2205.01989

M3 - Conference contribution

AN - SCOPUS:85137337054

T3 - Findings of the Association for Computational Linguistics: NAACL 2022 - Findings

SP - 962

EP - 979

BT - Findings of the Association for Computational Linguistics

Y2 - 10 July 2022 through 15 July 2022

ER -