Factors shaping non-expert trust in AI: A systematic snowballing review of explainable AI design considerations

Background Trust in artificial intelligence (AI) systems is critical for ethical and effective adoption, particularly among non-expert users. This review aimed to identify factors influencing trust and practical considerations for designing explainable AI (XAI) systems. Methods We systematically reviewed the literature following PRISMA 2020 guidelines and using backward and forward citation searches. The primary search was carried out in Web of Science (WoS), with the final search completed in January 2025. Eligible studies were peer-reviewed publications examining trust in AI among non-expert users and/or design considerations for XAI. Exclusion criteria removed studies focused solely on expert users or unrelated to trust or explainability. Results 35 studies involving diverse non-expert populations were included. We used a thematic synthesis approach to identify 33 trust-related factors grouped into personal characteristics, sociocultural influences, design and interaction attributes, and system-level properties (e.g., age, emotions, digital literacy, social norms, usability, aesthetics, explanation type, accuracy, transparency, regulatory compliance). Additionally, 120 design considerations were extracted across nine domains, including type and form of explanation; user experience and interaction; trust, transparency and human oversight; robustness, safety and reliability; data, traceability and the AI lifecycle; regulation and compliance; ethics, values and social responsibility; evaluation methods and metrics; and usage context and organizational factors. Conclusions The review synthesizes emerging perspectives on AI trust and explainability and identifies six domains that warrant further research to support the responsible design and deployment of XAI systems. Limitations include heterogeneous evaluation practices and inconsistent operationalization of trust among non-expert users, which complicates comparability across studies and hinder the responsible deployment of XAI systems.