Abstract
Detecting out-of-context media, such as “miscaptioned” images on Twitter, is a relevant problem, especially in domains of high public significance. In this work we aim to develop defenses against such misinformation for the topics of Climate Change, COVID-19, and Military Vehicles. We first present a large-scale multimodal dataset with over 884k tweets relevant to these topics. Next, we propose a detection method, based on the state-of-the-art CLIP model, that leverages automatically generated hard image-text mismatches. While this approach works well on our automatically constructed out-of-context tweets, we aim to validate its usefulness on data representative of the real world. Thus, we test it on a set of human-generated fakes, created by mimicking in-the-wild misinformation. We achieve an 11% detection improvement in a high precision regime over a strong baseline. Finally, we share insights about our best model design and analyze the challenges of this emerging threat.- Anthology ID:
- 2022.naacl-main.110
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1530–1549
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.110
- DOI:
- 10.18653/v1/2022.naacl-main.110
- Cite (ACL):
- Giscard Biamby, Grace Luo, Trevor Darrell, and Anna Rohrbach. 2022. Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1530–1549, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation (Biamby et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.naacl-main.110.pdf
- Code
- giscardbiamby/twitter-comms
- Data
- Twitter-COMMs