CoUX: Collaborative Visual Analysis of Think-Aloud Usability Test Videos for Digital Interfaces

Ehsan Jahangirzadeh Soure, Emily Kuang, Mingming Fan, Jian Zhao

View presentation:2021-10-28T13:00:00ZGMT-0600Change your timezone on the schedule page
Exemplar figure, described by caption below
CoUX is a collaborative visual analytics tool to support multiple UX evaluators with analyzing think-aloud usability test recordings. From an input video, a video analysis engine extracts various types of features, which are stored on a back-end and presented on a front-end visual interface to facilitate the identification of usability problems among UX evaluators. Moreover, the front-end, consisting of three interactively coordinated panels, communicates with the back-end to support individual problem logging and annotation as well as collaboration amongst a team of UX evaluators.
Fast forward

Direct link to video on YouTube:


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.