Measuring User Experience Through Speech Analysis: Insights from HCI Interviews

2025-03-31

AI Summary

Traditional subjective questionnaires for assessing user experience (UX) are prone to cognitive and response biases, limiting objectivity and ecological validity. Method: This study proposes an objective, speech-based UX quantification framework. We extract acoustic features (e.g., RMS, zero-crossing rate), prosodic features (e.g., jitter, shimmer), and socio-linguistic features (e.g., vocal activity, engagement) to construct a multidimensional speech feature space. Statistical hypothesis testing and behavioral modeling are then applied to automatically discriminate between positive and neutral UX states. Contribution/Results: To our knowledge, this is the first systematic integration of multi-source speech features into UX evaluation—eliminating reliance on subjective Likert scales and establishing a non-intrusive, real-time, bias-robust paradigm. Experimental results demonstrate statistically significant separation of UX states (p < 0.01); RMS, shimmer, and vocal activity emerge as key discriminative indicators. We release a fully reproducible, open-source toolchain, advancing objective, data-driven UX assessment in human–computer interaction research.

Technology Category

• Humans and AI: User Experience and Usability
• Natural Language Processing: Speech
• Machine Learning: Feature Construction/Reformulation

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

User satisfaction plays a crucial role in user experience (UX) evaluation. Traditionally, UX measurements are based on subjective scales, such as questionnaires. However, these evaluations may suffer from subjective bias. In this paper, we explore the acoustic and prosodic features of speech to differentiate between positive and neutral UX during interactive sessions. By analyzing speech features such as root-mean-square (RMS), zero-crossing rate(ZCR), jitter, and shimmer, we identified significant differences between the positive and neutral user groups. In addition, social speech features such as activity and engagement also show notable variations between these groups. Our findings underscore the potential of speech analysis as an objective and reliable tool for UX measurement, contributing to more robust and bias-resistant evaluation methodologies. This work offers a novel approach to integrating speech features into UX evaluation and opens avenues for further research in HCI.

Problem

• Objective UX measurement using speech analysis
• Differentiating positive and neutral UX via acoustic features
• Reducing subjective bias in UX evaluation methods

Innovation

• Using acoustic features for UX evaluation
• Analyzing prosodic speech differences
• Integrating social speech features