Data Subjects' Perspectives on Emotion Artificial Intelligence Use in the Workplace: A Relational Ethics Lens

The workplace has experienced extensive digital transformation, in part due to artificial intelligence's commercial availability. Though still an emerging technology, emotional artificial intelligence (EAI) is increasingly incorporated into enterprise systems to augment and automate organizational decisions and to monitor and manage workers. EAI use is often celebrated for its potential to improve workers' wellbeing and performance as well as address organizational problems such as bias and safety. Workers subject to EAI in the workplace are data subjects whose data make EAI possible and who are most impacted by it. However, we lack empirical knowledge about data subjects' perspectives on EAI, including in the workplace. To this end, using a relational ethics lens, we qualitatively analyzed 395 U.S. adults' open-ended survey (partly representative) responses regarding the perceived benefits and risks they associate with being subjected to EAI in the workplace. While participants acknowledged potential benefits of being subject to EAI (e.g., employers using EAI to aid their wellbeing, enhance their work environment, reduce bias), a myriad of potential risks overshadowed perceptions of potential benefits. Participants expressed concerns regarding the potential for EAI use to harm their wellbeing, work environment and employment status, and create and amplify bias and stigma against them, especially the most marginalized (e.g., along dimensions of race, gender, mental health status, disability). Distrustful of EAI and its potential risks, participants anticipated conforming to (e.g., partaking in emotional labor) or refusing (e.g., quitting a job) EAI implementation in practice. We argue that EAI may magnify, rather than alleviate, existing challenges data subjects face in the workplace and suggest that some EAI-inflicted harms would persist even if concerns of EAI's accuracy and bias are addressed.