Conducting Design Science Research in Society 5.0 – Proposal of an Explainable Artificial Intelligence Research Methodology

Abstract

Every technological or scientific advance is accompanied by a change in social structures, moral concepts, laws and education. As more and more people gain access to the digital world and the technical possibilities increase at the same rate, the excitement to carry out computer-based engineering projects increases. This in turn leads to an elevated demand for appropriate design-oriented methodologies, especially from the field of design science research (DSR), which in a sense democratize digital engineering. The idea of Society 5.0 is one of the major shifts in perspective on the role of technology, humans and their interaction in a shared living world. As a core component, artificial intelligence (AI), together with the Internet of things and big data analytics, is expected to have the most significant impact on the transformation toward smart societies. In this study, a systematic literature review of a total of 137 published articles addressing AI projects using DSR methodologies is conducted with the purpose of establishing a unified methodology for explainable AI-focused DSR projects. The proposed methodology further takes into account the particularities of AI at the varying advanced levels of artificial narrow intelligence (ANI) to the presumed necessities for approaching artificial general intelligence (AGI), which has not yet been fully realized. By allowing AI researchers to rely on a generalized methodological approach, the gap between behavioral science and design science is bridged, with the former laying the foundation for understanding living reality and the latter developing the means to mimic that reality as part of artificiality.