TY - JOUR
T1 - Expectations of artificial intelligence and the performativity of ethics
T2 - Implications for communication governance
AU - Kerr, Aphra
AU - Barry, Marguerite
AU - Kelleher, John D.
N1 - Publisher Copyright:
© The Author(s) 2020.
PY - 2020/1
Y1 - 2020/1
N2 - This article draws on the sociology of expectations to examine the construction of expectations of ‘ethical AI’ and considers the implications of these expectations for communication governance. We first analyse a range of public documents to identify the key actors, mechanisms and issues which structure societal expectations around artificial intelligence (AI) and an emerging discourse on ethics. We then explore expectations of AI and ethics through a survey of members of the public. Finally, we discuss the implications of our findings for the role of AI in communication governance. We find that, despite societal expectations that we can design ethical AI, and public expectations that developers and governments should share responsibility for the outcomes of AI use, there is a significant divergence between these expectations and the ways in which AI technologies are currently used and governed in large scale communication systems. We conclude that discourses of ‘ethical AI’ are generically performative, but to become more effective we need to acknowledge the limitations of contemporary AI and the requirement for extensive human labour to meet the challenges of communication governance. An effective ethics of AI requires domain appropriate AI tools, updated professional practices, dignified places of work and robust regulatory and accountability frameworks.
AB - This article draws on the sociology of expectations to examine the construction of expectations of ‘ethical AI’ and considers the implications of these expectations for communication governance. We first analyse a range of public documents to identify the key actors, mechanisms and issues which structure societal expectations around artificial intelligence (AI) and an emerging discourse on ethics. We then explore expectations of AI and ethics through a survey of members of the public. Finally, we discuss the implications of our findings for the role of AI in communication governance. We find that, despite societal expectations that we can design ethical AI, and public expectations that developers and governments should share responsibility for the outcomes of AI use, there is a significant divergence between these expectations and the ways in which AI technologies are currently used and governed in large scale communication systems. We conclude that discourses of ‘ethical AI’ are generically performative, but to become more effective we need to acknowledge the limitations of contemporary AI and the requirement for extensive human labour to meet the challenges of communication governance. An effective ethics of AI requires domain appropriate AI tools, updated professional practices, dignified places of work and robust regulatory and accountability frameworks.
KW - Ethics
KW - artificial intelligence
KW - communication governance
KW - expectations
KW - performativity
KW - science and technology studies
UR - http://www.scopus.com/inward/record.url?scp=85084658386&partnerID=8YFLogxK
U2 - 10.1177/2053951720915939
DO - 10.1177/2053951720915939
M3 - Article
SN - 2053-9517
VL - 7
JO - Big Data and Society
JF - Big Data and Society
IS - 1
ER -