This study proposed an augmented reality query-answering system (AR-QAS) based on mobile cloud
computing to provide natural language informational navigation services. Empirical research was performed to examine the effectiveness of the system in actual use. This study confirms that the new model
developed by combining technology acceptance model (TAM), media richness theory, and the factors of
self-efficacy can be applied to relevant AR research. The experiment results revealed that the average
question classification accuracy of QAS when combined with artificial neural network and ontology
was 98.76%. Moreover, the perceived media richness was found to be positively related to self-efficacy,
perceived usefulness, perceived ease of use, user attitude, and use intention. Furthermore, this study
reveals that combining the TAM and media richness theory provides a stronger explanation than does
the TAM alone. Before new systems are created, designers are suggested to consider the four factors of
media richness theory (i.e., multiple cues, language variety, timely feedback, and personal focus), to
greatly improve user attitudes toward and behavioral intentions to use new technologies.