A Method for Increasing User Engagement with Voice Assistant System

Abstract

Voice interaction is becoming one of the major methods of human interaction with computers. Several mobile service providers have introduced various types of voice assistant systems such as Bixby from Samsung, Siri from Apple, and Google Assistant from Google that provide information including the schedule for a day, the weather, or methods to control the device to perform a task such as playing music. Although the voice assistant system provides various types of functions, generally, the users do not understand what functions the system can support. We conducted a control task analysis based on expert interviews and found that the main bottleneck of using a voice assistant system is that the user cannot know all the commands. Thus, we believe that presenting recommendable commands is an effective way to increase user engagement. Through buzz data analysis, we discovered what functions could be used and determined the relevant usage context. Subsequently, we performed context modelling and designed the user interface (UI) of a voice assistant system and conducted a case study. Through this case study, we proved that presenting commands on a UI induced more user engagement and usability.