A Multimodal Deep Log-Based User Experience (UX) Platform for UX Evaluation

Abstract

The user experience (UX) is an emerging field in user research and design, and the development of UX evaluation methods presents a challenge for both researchers and practitioners. Different UX evaluation methods have been developed to extract accurate UX data. Among UX evaluation methods, the mixed-method approach of triangulation has gained importance. It provides more accurate and precise information about the user while interacting with the product. However, this approach requires skilled UX researchers and developers to integrate multiple devices, synchronize them, analyze the data, and ultimately produce an informed decision. In this paper, a method and system for measuring the overall UX over time using a triangulation method are proposed. The proposed platform incorporates observational and physiological measurements in addition to traditional ones. The platform reduces the subjective bias and validates the user’s perceptions, which are measured by different sensors through objectification of the subjective nature of the user in the UX assessment. The platform additionally offers plug-and-play support for different devices and powerful analytics for obtaining insight on the UX in terms of multiple participants.

UXmood—A Sentiment Analysis and Information Visualization Tool to Support the Evaluation of Usability and User Experience

“…In this context, Law et al [2] proposed expanding the scope of user experience analysis to include, in addition to usability factors, the emotional factor to provide new metrics that may better reflect user sentiment while using the system. Despite the challenges of using this approach [9], there are already several automatic extraction methods that can be used to generate user sentiment data [6,7] using various sensors [8].…”

“…Among the analyzed works, only a few [8,30,31] use multimodal sentiment analysis techniques to evaluate user experience or usability. The more common type of classification is textual, whether in audio transcription or product reviews on the Internet [1,8,[30][31][32][33][34]. References [8,30,31,33,35] record the user's face for use in sentiment analysis algorithms based on facial expressions.…”

“…The more common type of classification is textual, whether in audio transcription or product reviews on the Internet [1,8,[30][31][32][33][34]. References [8,30,31,33,35] record the user's face for use in sentiment analysis algorithms based on facial expressions. User speech capture is present in six works [8,[30][31][32][33]36] but only four works [8,30,31,36] use audio features to perform sentiment analysis.…”

“…References [8,30,31,33,35] record the user's face for use in sentiment analysis algorithms based on facial expressions. User speech capture is present in six works [8,[30][31][32][33]36] but only four works [8,30,31,36] use audio features to perform sentiment analysis.…”

“…References [1,8,30,[35][36][37][38][39][40] present some data visualization techniques to represent the results, with the most common being wordcloud, heatmap, and histogram. Only two studies [8,36] use sensors, such as eye trackers, to identify the area that the user is observing.…”