Human-AI interaction: An emerging interdisciplinary domain for enabling human-centered AI
This work addresses the problem of developing safe and beneficial AI systems for society by introducing an interdisciplinary framework, though it is incremental as it builds on a previously proposed approach.
The paper tackles the lack of systematic interdisciplinary approaches to address new challenges in AI development that can harm humans, proposing the 'Human-AI Interaction' domain to enable 'Human-Centered AI' and outlining its objectives, methodology, and future research agenda.
The new characteristics of AI technology have brought new challenges to the research and development of AI systems. AI technology has benefited humans, but if improperly developed, it will harm humans. At present, there is no systematic interdisciplinary approach to effectively deal with these new challenges. This paper analyzes the new challenges faced by AI systems and further elaborates the "Human-Centered AI" (HCAI) approach we proposed in 2019. In order to enable the implementation of the HCAI approach, we systematically propose an emerging interdisciplinary domain of "Human-AI Interaction" (HAII), and define the objective, methodology, and scope. Based on literature review and analyses, this paper summarizes the main areas of the HAII research and application as well as puts forward the future research agenda for HAII. Finally, the paper provides strategic recommendations for future implementation of the HCAII approach and HAII work.