Understanding users’ effective use of generative conversational AI from a media naturalness perspective: a hybrid structural equation modeling-artificial neural network (SEM-ANN) approach

Although generative conversational artificial intelligence (AI) can answer questions well and hold conversations as a person, the semantic ambiguity inherent in text-based communication poses challenges to effective use. Effective use reflects the users’ utilization of generative conversational AI to achieve their goals, which has not been previously studied. Drawing on the media naturalness theory, we examined how generative conversational AI’s content and style naturalness affect effective use. A two-wave survey was conducted to collect data from 565 users of generative conversational AI. Two techniques were used in this study. Initially, partial least squares structural equation modeling (PLS-SEM) was applied to determine the variables that significantly affected the mechanisms (i.e., cognitive effort and communication ambiguity) and effective use. Secondly, an artificial neural network model was used to evaluate the relative importance of the significant predictors of mechanisms and effective use identified from the PLS-SEM analysis. The results revealed that the naturalness of content and style differed in their effects on cognitive effort and communication ambiguity. Additionally, cognitive effort and communication ambiguity negatively affected effective use. This study advances the literature on effective use by uncovering the psychological mechanisms underlying effective use and their antecedents. In addition, this study offers insights into the design of generative conversational AI.