An error management approach to perceived fakeness of deepfakes: The moderating role of perceived deepfake targeted politicians’ personality characteristics

The present study examined individuals’ perceived message and video fakeness of deepfake (versus real) videos and deepfake-described (versus non-described) videos, and the moderating effect of perceived deepfake targeted politicians’ personality characteristics on the perceived fakeness of deepfake videos. Six hundred and one participants were randomly assigned to one of the four groups: deepfake-described deepfake videos (n = 148), non-described deepfake videos (n = 157), deepfake-described real videos (n = 143), and non-described real videos (n = 153). Participants in each group watched deepfake or real Trump and Obama videos, and then answered questions about their perceived fakeness of each video and the perceived dangerousness and trustworthiness of the video target. Results indicated that participants were able to make the correct decisions to perceive the deepfake and deepfake-described videos and messages as less realistic than real and non-described videos. As predicted by error management theory, participants were inclined to commit the less costly false positive error to perceive dangerous video targets’ messages in real and non-described videos as fake as deepfake and deepfake-described videos. In contrast, they were prone to make the less costly false negative error to perceive trustworthy video targets’ messages in deepfake videos, and the deepfake videos, as real as real videos. Theoretical and practical implications for deepfakes research were discussed.