Ethical dimensions of AI-supported fact-checking in elderly health care: a qualitative exploratory study

Abstract

This article examines the ethical dimensions of AI-supported fact-checking tools in the context of elderly health care, focusing on how caregivers interpret trust, credibility, and cultural relevance when engaging with AI-mediated information. The study adopts a qualitative, exploratory methodology grounded in Value Sensitive Design and Human-Machine Communication. Empirical data were collected through a co-design workshop, focus group discussions, empathy map exercises, and descriptive questionnaires with elderly caregivers in a rural Portuguese context. Rather than aiming for statistical generalization, the research prioritizes contextual understanding and value articulation. The findings reveal that caregivers evaluate AI-supported fact-checking solutions not only in terms of informational accuracy, but also through ethical considerations such as protection, inclusion, trustworthiness, and perceived legitimacy. Differences between traditional journalistic approaches, automated AI solutions, and visual or animated formats were less salient than participants' interpretations of how these tools aligned with their lived experiences and communicative norms. By foregrounding the perspectives of caregivers in a socioeconomically constrained setting, this study contributes empirically grounded insights to debates in AI ethics and responsible AI design. It highlights the importance of culturally sensitive, user-centered approaches when deploying AI technologies in health communication and misinformation management, particularly for vulnerable populations.