Being Proactive for Responsible AI: Analyzing Multiple Sectors for Innovation via Systematic Literature Review

Background: Questions surrounding the ethics of artificial intelligence (AI) have been debated for decades [1]. However, in recent years there have been multiple initiatives, scholarly reviews, and policy documents to identify and define ethical issues in play [2]. The efforts to bring high-level principles to applicable practice are complex and can be lost in translation [3]. Moreover, a call to be proactive, rather than reactive, stems from a deduction of intentions behind responsible innovation, value-centric design principles, education efforts, and representative data management techniques. Contemporary applications of AI are complex and difficult to explain, edit, and deal with once integrated in a natural system [4] [5]. Therefore, the analysis conducted within this systematic literature review (SLR) will clarify methods to promote and engage practice on the front end of ethical and responsible AI. As such, the research question is explored: How does each helix in the Quintuple Innovation model address responsible and ethical AI technology with anticipatory or proactive approaches? Methods: To conduct this ongoing research, an adaptation of the PRISMA framework and Hess & Fore's 2017 methodological approach guides the SLR [6] [7]. We included journal articles that were written in English and published between 2018-2023. The collected studies aim to examine how academic scholarship approaches to responsible AI within academia, government, industry, civil society, or the natural environment (the Quintuple Helix). The Web of Science, Google Scholar, and PhilPapers databases were used to identify a set of prominent publications in this field: AI & Society, Nature Machine Intelligence, Minds and Machines, IEEE Transactions on Technology and Society, AI and Ethics, Science and Engineering Ethics, and Communications of the ACM. A key limitation of this study is that it cannot gather the entirety of literature written about the topics of proactively promoting ethical AI due to the vast size and definitional complexity of the associated fields. These inclusion criteria allow the researchers to manage the data and draw meaningful insights from the most current thinking that is reflected in the rapid development of AI innovation we see today. Results and discussion: This poster will present preliminary results and the theoretical framework that guided the qualitative coding process. Additionally, this poster will serve as a forum to collect experts' opinions about what they would like to see from this SLR dataset, and how we can incorporate those elements into our coding. As a result, this data will be able to inform future work to investigate multiple gaps in the literature. For instance, U.S. Government work not protected by U.S. copyright this study will result in a theoretical framework that identifies proactive approaches to responsible and sustainable AI aligned with the five sectors for innovation. Inspired from [8], the effects of investments in education, and other sectors, will be mapped as a chain of responsible AI innovation across all innovation sectors. Finally, we can draw informed conclusions about the use and misuse of experts in AI, ethics, education, and policy. By working towards these objectives, we can see how the interdisciplinary field has made (or not made) a collective effort toward promoting responsible AI-filling a gap in the literature that highlights proactive approaches, rather than reactive. In conclusion, this data will inform experts across multiple domains about how to approach and organize a concerted effort to promote ethical and responsible AI in a pragmatic way.