What Does it Mean to Trust a Robot?

Abstract

Research on trust in human-human interaction has typically focused on notions of vulnerability, integrity, and exploitation whereas research on trust in human-machine interaction has typically focused on competence and reliability. In this initial study, we explore whether these different aspects of trust can be considered parts of a multidimensional conception and measure of trust. We gathered 62 words from dictionaries and trust literatures and asked participants to evaluate the words as belonging to a personal meaning or a capacity meaning. Through an iterative process using Principal Components Analysis (PCA) and item analysis, we derived four components that capture the multidimensional space occupied by the concept of trust. The resulting four components yield four subscales of trust with five items each and alpha reliabilities as follows: Capable = .88, Ethical = .87, Sincere = .84, and Reliable = .72.