Finding the Right Voice: Exploring the Impact of Gender Similarity and Gender-Role Congruity on the Efficacy of Automated Vehicle Explanations

Zhang, Qiaoning · 2024 · Proceedings of the AAAI Symposium Series

DOI: 10.1609/aaaiss.v2i1.27675

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This document outlines a proposed research study investigating how the gender of automated vehicle (AV) explanation voices influences user trust. The authors address a critical gap in human-AV interaction literature: while explanations are known to enhance trust by clarifying vehicle reasoning, the specific impact of voice characteristics, particularly gender, remains underexplored. The study is motivated by the need to accelerate AV adoption, which is currently hindered by public apprehension and lack of trust. Drawing on gender-role congruity theory and similarity attraction theory, the researchers aim to determine whether matching the AV voice gender to the user’s gender or to the perceived role of the AV (e.g., assistant vs. supervisor) enhances trust efficacy. The proposed methodology employs a between-subjects experimental design conducted via an online survey platform. The target population consists of U.S. drivers with valid licenses. The study utilizes a 2x2 factorial design manipulating two independent variables: gender similarity (whether the AV voice matches the participant’s gender) and gender-role congruity (whether the voice gender aligns with the participant’s perception of the AV’s role, categorized as either a “driving assistant” or “driving supervisor”). Participants will view six video scenarios depicting AV behavior in urban, highway, and rural contexts, accompanied by “what+why” auditory explanations. Trust will be measured as the dependent variable using a seven-item scale adapted from McAllister (1995) and Lee and Lee (2022), rated on a 7-point Likert scale. The authors plan to conduct a pilot study and perform statistical power analysis to determine the required sample size, aiming for 80% power at an alpha level of .05. As this is a research proposal, no empirical results or findings are reported. Instead, the authors outline anticipated contributions to the field. They expect the study to clarify whether voice gender should be static or dynamically tailored to user demographics and perceived AV roles. The findings are projected to inform the design of AV systems by identifying optimal voice characteristics that foster trust and mitigate design pitfalls. Furthermore, the study aims to provide a theoretical foundation for future research into other voice attributes and demographic factors, such as age, race, and cultural differences, ultimately supporting the development of more intuitive and user-centric human-AV interactions.

Methodology

lab_experiment

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via unpaywall on 2026-05-06 (37 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• acceptance adoption