AI-Supported User Experience Evaluation: A Systematic Literature Review

With the growing prevalence of digital systems, the demand for scalable approaches for evaluating user experience (UX) is increasing, as traditional UX evaluation methods often reach their limits due to high manual effort, limited scalability, and restricted contextual coverage. In this context, artificial intelligence (AI) is increasingly explored as a methodological extension to support and enhance UX evaluation processes. This paper presents a systematic literature review that examines the current state of research on AI-supported approaches for UX evaluation and comparatively classifies applied AI methods, utilized data sources, evaluation characteristics, as well as reported strengths, limitations, and research gaps. The study follows a structured review protocol, including a systematic literature search, a multi-stage screening process, and the analysis of both scientific publications and practice-oriented sources. The results indicate that AI-based approaches primarily assume a supportive role within UX evaluation, particularly in the analysis of large-scale UX evaluation datasets, automated detection of usability issues, and the evaluation of emotional and cognitive user responses. Text-based feedback and behavioral interaction data dominate current approaches, while highly automated methods are still rarely validated through systematic empirical studies under realistic usage conditions. Overall, the findings show that AI-supported approaches do not replace classical UX evaluation methods but meaningfully complement them by enhancing scalability and analytical depth, while methodological limitations and a substantial need for further research remain, particularly regarding multimodal data integration, transparency, and robust empirical validation.