Trust and interaction design in AI-enabled systems: a systematic literature review

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

As artificial intelligence (AI) becomes increasingly integrated into everyday systems, understanding how users perceive and interact with AI is critical for effective design. This systematic literature review analyzes 1,565 peer-reviewed scholarly articles published post-2023 from IEEE Xplore, ACM Digital Library, Scopus, and Web of Science, ultimately including 33 publications that met the inclusion criteria. Following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework, this review examines how user trust in AI-enabled systems is defined and measured, and which interaction design factors influence it. The findings reveal that the literature reflects diverse contributions from authors, institutions, and disciplines, while also employing varied definitions and methodologies, contributing to a fragmented body of work. In addition, this review identifies nine key design factors, including explainability, anthropomorphism, confidence, interface, errors, security, transparency, competence, and perceived control. Overall, greater consensus within the field is needed to support the development of stronger and more cohesive bodies of work for each design factor.