“I know it’s a deepfake”: the role of AI disclaimers and comprehension in the processing of deepfake parodies

Abstract

Rapid innovations in media technologies have ushered in diverse entertainment avenues, including politically oriented content, presenting both novel opportunities and societal challenges. This study delves into the implications of the burgeoning deepfake phenomenon, particularly focusing on audience interpretation and engagement with deepfake parodies, a quintessential example of “misinfotainment.” Additionally, it examines the potential impact of artificial intelligence (AI) disclaimers on audience understanding and related consequences. To probe this, two experiments (N = 2,808) were executed featuring parodied politicians adopting opposing viewpoints on the issue of climate change. U.S. participants were either exposed to deepfake videos prefaced with AI disclaimers or without. Results indicate that the inclusion of an AI disclaimer significantly influenced audience comprehension and their ability to recognize the parody. These factors were subsequently associated with enjoyment, discounting, and counterarguing, which in turn showed different relationships with policy support and sharing intentions. This article culminates with insights into the theoretical underpinnings and practical ramifications of these findings.