Details
| Original language | English |
|---|---|
| Title of host publication | Findings of the Association for Computational Linguistics |
| Subtitle of host publication | NAACL 2022 - Findings |
| Pages | 962-979 |
| Number of pages | 18 |
| ISBN (electronic) | 9781955917766 |
| Publication status | Published - Jul 2022 |
| Event | 2022 Findings of the Association for Computational Linguistics: NAACL 2022 - Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022 |
Publication series
| Name | Findings 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 subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Findings of the Association for Computational Linguistics: NAACL 2022 - Findings. 2022. p. 962-979 (Findings of the Association for Computational Linguistics: NAACL 2022 - Findings).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
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 - https://doi.org/10.48550/arXiv.2205.01989
DO - https://doi.org/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 -