Virtual vs. human influencer: Effects on users' perceptions and brand outcomes

In the recent wave of artificial intelligence-based innovations, Virtual influencers (VIs) are one of the newest and most promising innovations. Despite their indisputable potential, still little is known about users' reactions to non-human endorsers. Our experimental study investigates users' perceptions of VIs engaged in sponsorship activities on Instagram, examining the impact of the influencer's nature (human vs. virtual) and possible interaction effects of the type of message conveyed (hedonic vs. utilitarian) on the influencer and brand-related variables. In line with the idea that individuals apply human social rules when interacting with computers, as established in the CASA paradigm, our results from an online sample (N = 238) show that disclosing the synthetic nature of a fully anthropomorphized virtual persona does not affect influencer and brand perceptions. Despite virtual influencers' objective lack of capacity to perceive and feel affective and sensorial information, their acceptance by the users is not hindered by an emotion-based communicative style. The research provides social and business implications for companies aiming to implement virtual influencers successfully.