Title Effects of an Agent Feature Comprehension on the Emotional Attachment of Users
Authors Yoshito Ogawa (Graduate School of Human Sciences, Waseda University)
Kaho Harada (School of Human Sciences, Waseda University)
Hideaki Kikuchi (Faculty of Human Sciences, Waseda University)
Abstract In this paper, we consider effects of an agent's comprehension of user features on a user's sense of emotional attachment to the agent. Recently, some research studies in Human-Agent Interaction (HAI) have examined the strategies that make users continue to use spoken dialogue systems over a long period of time. In this paper, we propose a system that discriminates a user's activity from the speech prosody and accumulates the prosody and the actual activity as training data to use in subsequent discrimination. Our results indicate that our proposed system performs more stable discrimination than heretofore, and that higher discrimination accuracy inspires a sense of emotional attachment more effectively.
PDF [Link]