Conspiracy thinking and social media use are associated with ability to detect deepfakes

Abstract

Deepfake videos are highly realistic manipulated videos that are often difficult to distinguish from authentic videos. The technology rapidly evolves, making deepfake videos increasingly realistic. Most research on deepfake videos is focused on the algorithmic detection of deepfakes. Less is known about the human recognition of deepfake videos. The aim of the current study was to investigate the predictors of human performance at recognizing deepfake videos. Our findings show that humans perform better at recognizing deepfake videos of familiar persons compared to deepfakes of unfamiliar persons. Next, our findings show a positive relationship between time spent on social media and deepfake detection performance, as well as conspiracy thinking and deepfake detection performance. No relationships were found between age and gender and deepfake detection performance.