Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
This addresses misinformation detection for high-public-significance domains, but it is incremental as it builds on existing CLIP models with new data and minor enhancements.
The paper tackled the problem of detecting out-of-context media, such as mis-captioned images on Twitter, focusing on topics like Climate Change, COVID-19, and Military Vehicles, and achieved an 11% detection improvement in a high precision regime over a strong baseline.
Detecting out-of-context media, such as "mis-captioned" 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.