🤖 AI Summary
This work addresses the critical challenge of software usability defect detection—traditionally reliant on manual inspection, resulting in high costs and low efficiency. To tackle this, we conduct a systematic literature review (SLR) augmented by topic modeling and cross-dimensional technology mapping, synthesizing insights from 155 peer-reviewed studies. This enables the first comprehensive, full-stack AI-driven usability detection taxonomy, spanning requirements, design, implementation, and evaluation phases. We identify six dominant technical paradigms, characterize methodological evolution trends, expose domain-specific adaptation bottlenecks, quantify key performance gaps (e.g., in contextual understanding and cross-platform generalizability), and uncover prevalent evaluation biases (e.g., overreliance on synthetic tasks or narrow benchmarks). The study delivers a scalable research roadmap, empirically grounded principles, and a methodological framework for AI-augmented usability engineering—substantially enhancing the systematicity, reproducibility, and practical applicability of automated usability assessment.
📝 Abstract
Usability issues can hinder the effective use of software. Therefore, various techniques are deployed to diagnose and mitigate them. However, these techniques are costly and time-consuming, particularly in iterative design and development. A substantial body of research indicates that automation and artificial intelligence can enhance the process of obtaining usability insights. In our systematic review of 155 publications, we offer a comprehensive overview of the current state of the art for automated usability issue detection. We analyze trends, paradigms, and the technical context in which they are applied. Finally, we discuss the implications and potential directions for future research.