Perceived value of AI-based recommendations service: the case of voice assistants

The application of artificial intelligence in services is continuously spreading. In particular, one of the most important recent trends is the development of virtual assistants, more particularly; voice assistants, which provide consumers with various services (e.g. information, music) and with product and service recommendations based on their preferences. There is a need to understand how valuable these recommendations are for consumers. This study contributes to the emerging body of research into consumers' use of the recommendations that voice assistants make in three key ways: (1) by analysing the roles of the benefits (i.e. convenience, compatibility, personalisation) they derive and costs they expend (i.e. cognitive effort, intrusiveness) in the value creation process related to voice assistants' recommendations; (2) by evaluating the effect of social presence (the key voice assistant feature) on perceived value of voice assistants' recommendations, through the benefits and costs associated with voice assistants and (3) by determining how the perceived value of voice assistants' recommendations affects consumer engagement. An online survey was used to collect data. Partial least squares structural equation modelling (PLS-SEM) was employed to analyse the conceptual model. The core findings of the study are as follows. First, social presence enhances the benefits (especially personalisation) and reduces the costs (except for cognitive effort) associated with voice assistants. Second, personalisation was shown to be the strongest determinant of the perceived value of voice assistants' recommendations, but their intrusiveness is a potential inhibitor in the way of increasing their value. Third, a positive relationship was observed between the perceived value of voice assistants' recommendations and consumer engagement with the assistants.