The impact of user characteristics and preferences on performance with an unfamiliar voice user interface

Abstract

Voice User Interfaces are increasing in popularity. However, their invisible nature with no or limited visuals makes it difficult for users to interact with unfamiliar VUIs. We analyze the impact of user characteristics and preferences on how users interact with a VUI-based calendar, DiscoverCal. While recent VUI studies analyze user behavior through self-reported data, we extend this research by analyzing both VUI usage data and self-reported data to observe correlations between both data types. Results from our user study (n=50) led to four key findings: 1) programming experience did not have a wide-spread impact on performance metrics while 2) assimilation bias did, 3) participants with more technical confidence exhibited a trial-and-error approach, and 4) desiring more guidance from our VUI correlated with performance metrics that indicate cautious users.