Mining human interactions to construct a virtual guide for a virtual fair

Abstract

In this paper we describe how we mine interactions between a human guide and a human visitor to build a virtual guide. A virtual guide is an agent capable of fulfilling the role of a human guide. Its goal is to guide visitors to each booth of a virtual fair and to provide information about the company or organization through interactive objects located at the fair. The guide decides what to say, using a graph search algorithm, and decides how to say using generation by selection based on contextual features. The guide decides where to speak at the virtual fair by creating clusters using a data classification algorithm to learn in what positions the human guide decided to talk.