AI-assisted usability analysis can potentially reduce the time and effort of finding usability problems, yet little is known about how AI's perceived expertise influences evaluators' analytic strategies and perceptions over time. We ran a within-subjects, five-session study (six hours per participant) with 12 professional UX evaluators who worked with two conversational assistants designed to appear novice- or expert-like (differing in suggestion quantity and response accuracy). We logged behavioral measures (number of passes, suggestion acceptance rate), collected subjective ratings (trust, perceived efficiency), and conducted semi-structured interviews. Participants experienced an initial novelty effect and a subsequent dip in trust that recovered over time. Their efficiency improved as they shifted from a two-pass to a one-pass video inspection approach. Evaluators ultimately rated the experienced CA as significantly more efficient, trustworthy, and comprehensive, despite not perceiving expertise differences early on. We conclude with design implications for adapting AI expertise to enable calibrated human-AI collaboration.

AI is promising in assisting UX evaluators with analyzing usability tests, but its judgments are typically presented as non-interactive visualizations. Evaluators may have questions about test recordings, but have no way of asking them. Interactive conversational assistants provide a Q&A dynamic that may improve analysis efficiency and evaluator autonomy. To understand the full range of analysis-related questions, we conducted a Wizard-of-Oz design probe study with 20 participants who interacted with simulated AI assistants via text or voice. We found that participants asked for five categories of information: user actions, user mental model, help from the AI assistant, product and task information, and user demographics. Those who used the text assistant asked more questions, but the question lengths were similar. The text assistant was perceived as significantly more efficient, but both were rated equally in satisfaction and trust. We also provide design considerations for future conversational AI assistants for UX evaluation.

Reviewing a think-aloud video is both time-consuming and demanding as it requires UX (user experience) professionals to attend to many behavioral signals of the user in the video. Moreover, challenges arise when multiple UX professionals need to collaborate to reduce bias and errors. We propose a collaborative visual analytics tool, CoUX, to facilitate UX evaluators collectively reviewing think-aloud usability test videos of digital interfaces. CoUX seamlessly supports usability problem identification, annotation, and discussion in an integrated environment. To ease the discovery of usability problems, CoUX visualizes a set of problem-indicators based on acoustic, textual, and visual features extracted from the video and audio of a think-aloud session with machine learning. CoUX further enables collaboration amongst UX evaluators for logging, commenting, and consolidating the discovered problems with a chatbox-like user interface. We designed CoUX based on a formative study with two UX experts and insights derived from the literature. We conducted a user study with six pairs of UX practitioners on collaborative think-aloud video analysis tasks. The results indicate that CoUX is useful and effective in facilitating both problem identification and collaborative teamwork. We provide insights into how different features of CoUX were used to support both independent analysis and collaboration. Furthermore, our work highlights opportunities to improve collaborative usability test video analysis.