How do people talk with a virtual philosopher: Log analysis of a real-world application

Abstract

Conversation with computers is an important form of human computer interaction. Inappropriately designed conversational agents can easily lead to unsatisfying user experience and even frustration, and this is especially true when the application is deployed in the real world. Currently, research on casual non-task oriented systems and our understanding in how people interact with such agents are still limited. To gain more insights on this issue, we carried out both quantitative and qualitative content analysis of conversation logs collected from a realworld application, featuring a non-task oriented conversational agent as a virtual philosopher. We construct a taxonomy of user utterances to the agent and discuss a few strategies that an agent might employ to provide a better user experience. © IFIP International Federation for Information Processing 2013.