Exploring Peoples' Perception of Autonomy and Reactance in Everyday AI Interactions

Applications using Artificial Intelligence (AI) have become commonplace and embedded in our daily lives. Much of our communication has transitioned from human–human interaction to human–technology or technology-mediated interaction. As technology is handed over control and streamlines choices and decision-making in different contexts, people are increasingly concerned about a potential threat to their autonomy. In this paper, we explore autonomy perception when interacting with AI-based applications in everyday contexts using a design fiction-based survey with 328 participants. We probed if providing users with explanations on “why” an application made certain choices or decisions influenced their perception of autonomy or reactance regarding the interaction with the applications. We also looked at changes in perception when users are aware of AI's presence in an application. In the social media context, we found that people perceived a greater reactance and lower sense of autonomy perhaps owing to the personal and identity-sensitive nature of the application context. Providing explanations on “why” in the navigation context, contributed to enhancing their autonomy perception, and reducing reactance since it influenced the users' subsequent actions based on the recommendation. We discuss our findings and the implications it has for the future development of everyday AI applications that respect human autonomy.