Managing turn-taking through beep sounds by Bixby: Applying conversation analysis to human-chatbot interaction constructions

Managing turn-taking through beep sounds by Bixby: Applying conversation analysis to human-chatbot interaction constructions

This paper explores turn-taking between users and Bixby, a Samsung voiceassistant. While using a simplified turn-taking system designed to guide users, Bixby doesnot fully understand and replicate the complex turn-taking system that characterizes humaninteraction. Utilizing Conversation Analysis (CA), this paper highlights the limitations ofBixby’s turn-taking system, which relies on mechanical cues such as ding↓↑ to indicate turninitiation and turn completion. These cues prove inadequate in accommodating the dynamicnature of human interaction, causing confusion in users regarding when and how to talkto the digital assistant. Users often predict turn endings based on their familiarity with humanturn-taking, which is often incompatible with Bixby’s rigid turn-taking mechanisms. Thisstudy incorporates insights form CA and applies sequential analysis to interactions betweenhumans and the voice digital assistant to explicate how Bixby’s turn-taking mechanisms becomeproblematic. This information helps explore ways to improve these interactions.