Responsible (use of) AI

Although there is a rich history of philosophical definitions of ethics when applied to human behavior, applying the same concepts and principles to AI may be fraught with problems. Anthropomorphizing AI to have characteristics such as "ethics" may promote a dangerous, unrealistic expectation that AI can be trained to have inherent, guaranteed ethical behavior. The authors instead advocate for increased research into the ethical use of AI from initial ideation and design through operational use and sustainment. The authors advocate for five key research areas: (1) education in ethics and core AI concepts for AI developers, leaders, and users, (2) development and use of model cards or datasheets for datasets to provide transparency into the strengths, limits, and potential biases of a trained model, (3) employing human-centered design that seeks to understand human value structures within a task context and enable effective human-machine interaction through intuitive and transparent interfaces, (4) targeted use of run time assurance that monitors and modifies the inputs or outputs of a trained model when necessary to enforce ethical principles such as safety or limiting bias, and (5) developing best practices for the use of a joint human-AI co-creation and training experience to enable a shared mental model and higher performance through potential emergent behavior.

Artificial intelligence and the work-health interface: A research agenda for a technologically transforming world of work

The labor market is undergoing a rapid artificial intelligence (AI) revolution. There is currently limited empirical scholarship that focuses on how AI adoption affects employment opportunities and work environments in ways that shape worker health, safety, well-being and equity. In this article, we present an agenda to guide research examining the implications of AI on the intersection between work and health. To build the agenda, a full day meeting was organized and attended by 50 participants including researchers from diverse disciplines and applied stakeholders. Facilitated meeting discussions aimed to set research priorities related to workplace AI applications and its impact on the health of workers, including critical research questions, methodological approaches, data needs, and resource requirements. Discussions also aimed to identify groups of workers and working contexts that may benefit from AI adoption as well as those that may be disadvantaged by AI. Discussions were synthesized into four research agenda areas: (1) examining the impact of stronger AI on human workers; (2) advancing responsible and healthy AI; (3) informing AI policy for worker health, safety, well-being, and equitable employment; and (4) understanding and addressing worker and employer knowledge needs regarding AI applications. The agenda provides a roadmap for researchers to build a critical evidence base on the impact of AI on workers and workplaces, and will ensure that worker health, safety, well-being, and equity are at the forefront of workplace AI system design and adoption.

Executive-centered AI? Designing predictive systems for the public sector

Recent policies and research articles call for turning AI into a form of IA ('intelligence augmentation'), by envisioning systems that center on and enhance humans. Based on a field study at an AI company, this article studies how AI is performed as developers enact two predictive systems along with stakeholders in public sector accounting and public sector healthcare. Inspired by STS theories about values in design, we analyze our empirical data focusing especially on how objectives, structured performances, and divisions of labor are built into the two systems and at whose expense. Our findings reveal that the development of the two AI systems is informed by politically motivated managerial interests in cost-efficiency. This results in AI systems that are (1) designed as managerial tools meant to enable efficiency improvements and cost reductions, and (2) enforced on professionals on the 'shop floor' in a top-down manner. Based on our findings and a discussion drawing on literature on the original visions of human-centered systems design from the 1960s, we argue that turning AI into IA seems dubious, and ask what human-centered AI really means and whether it remains an ideal not easily realizable in practice. More work should be done to rethink human-machine relationships in the age of big data and AI, in this way making the call for ethical and responsible AI more genuine and trustworthy.

Decision trees: from efficient prediction to responsible AI

This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.

Towards Context-Aware Facial Emotion Reaction Database for Dyadic Interaction Settings

Emotion recognition is a significant issue in many sectors that use human emotion reactions as communication for marketing, technological equipment, or human-robot interaction. The realistic facial behavior of social robots and artificial agents is still a challenge, limiting their emotional credibility in dyadic face-to-face situations with humans. One obstacle is the lack of appropriate training data on how humans typically interact in such settings. This article focused on collecting the facial behavior of 60 participants to create a new type of dyadic emotion reaction database. For this purpose, we propose a methodology that automatically captures the facial expressions of participants via webcam while they are engaged with other people (facial videos) in emotionally primed contexts. The data were then analyzed using three different Facial Expression Analysis (FEA) tools: iMotions, the Mini-Xception model, and the Py-Feat FEA toolkit. Although the emotion reactions were reported as genuine, the comparative analysis between the aforementioned models could not agree with a single emotion reaction prediction. Based on this result, a more-robust and -effective model for emotion reaction prediction is needed. The relevance of this work for human-computer interaction studies lies in its novel approach to developing adaptive behaviors for synthetic human-like beings (virtual or robotic), allowing them to simulate human facial interaction behavior in contextually varying dyadic situations with humans. This article should be useful for researchers using human emotion analysis while deciding on a suitable methodology to collect facial expression reactions in a dyadic setting.

Audience-Dependent Explanations for AI-Based Risk Management Tools: A Survey

Artificial Intelligence (AI) is one of the most sought-after innovations in the financial industry. However, with its growing popularity, there also is the call for AI-based models to be understandable and transparent. However, understandably explaining the inner mechanism of the algorithms and their interpretation is entirely audience-dependent. The established literature fails to match the increasing number of explainable AI (XAI) methods with the different stakeholders' explainability needs. This study addresses this gap by exploring how various stakeholders within the Swiss financial industry view explainability in their respective contexts. Based on a series of interviews with practitioners within the financial industry, we provide an in-depth review and discussion of their view on the potential and limitation of current XAI techniques needed to address the different requirements for explanations.

Road map for research on responsible artificial intelligence for development (AI4D) in African countries: The case study of agriculture

Individuals from a diverse range of backgrounds are increasingly engaging in research and development in the field of artificial intelligence (AI). The main activities, although still nascent, are coalescing around three core activities: innovation, policy, and capacity building. Within agriculture, which is the focus of this paper, AI is working with converging technologies, particularly data optimization, to add value along the entire agricultural value chain, including procurement, farm automation, and market access. Our key takeaway is that, despite the promising opportunities for development, there are actual and potential challenges that African countries need to consider in deciding whether to scale up or down the application of AI in agriculture. Input from African innovators, policymakers, and academics is essential to ensure that AI solutions are aligned with African needs and priorities. This paper proposes questions that can be used to form a road map to inform research and development in this area.

Let Me Take Over: Variable Autonomy for Meaningful Human Control

As Artificial Intelligence (AI) continues to expand its reach, the demand for human control and the development of AI systems that adhere to our legal, ethical, and social values also grows. Many (international and national) institutions have taken steps in this direction and published guidelines for the development and deployment of responsible AI systems. These guidelines, however, rely heavily on high-level statements that provide no clear criteria for system assessment, making the effective control over systems a challenge. "Human oversight" is one of the requirements being put forward as a means to support human autonomy and agency. In this paper, we argue that human presence alone does not meet this requirement and that such a misconception may limit the use of automation where it can otherwise provide so much benefit across industries. We therefore propose the development of systems with variable autonomy-dynamically adjustable levels of autonomy-as a means of ensuring meaningful human control over an artefact by satisfying all three core values commonly advocated in ethical guidelines: accountability, responsibility, and transparency.