Vocalizing User Feedback: The Impact of Input Modality on Self-Disclosure

Abstract

This study explores how input modality - voice versus text - affects self-disclosure in user feedback, leveraging a novel approach that uses transformer-based models to detect self-disclosure per token embedded in context. In an online experiment with 122 participants, results indicate that participants using voice input engaged significantly less in self-disclosure than those using text, a finding associated with reduced perceived anonymity in voice interactions. This effect persisted after accounting for response length, suggesting that the influence of voice input on self-disclosure is not merely due to brevity but also reflects unique psychological responses to voice-based communication. These findings contribute to a deeper theoretical understanding of input modality's role in shaping disclosure behavior in user feedback contexts. Practical implications offer design guidance for voice-based feedback systems to encourage more open and authentic feedback in sensitive settings.