Sociotechnical Perspectives on AI Ethics and Accountability

The articles in this special section focus on sociotechnical perspectives on artificial intelligence (AI) ethics and accountability. Suppose we were to develop a loan-processing tool based on artificial intelligence (AI) to process applications by people for financial loan products. The tool would consider application data and recommend whether to give a loan and for how much. It would even seek out prospective borrowers online for new business and offer loans. Or, suppose we were to develop a career coach that recommends career tracks and training based on a user’s career goal, biosketch, and time and money available to invest in training. Applications of AI in decision support are not hypothetical, and applications such as loan processing and career coaching are becoming mainstream. However, although like other algorithms, their inputs and outputs are data; these AI applications are embedded in society, their decisions and recommendations have direct effects on people’s lives. Denial of a loan reduces financial options and may harm a borrower’s wellbeing, while giving a loan but at usurious interest rates might expose a borrower to financial ruin. Likewise, whereas career advice can be valuable to someone who does not have strong mentors, narrow or biased career advice can impede their future and, through them, their family’s prospects.