Web Mining in the EVA Intelligent Agent Architecture

This paper describes the architecture of the fourth version of the evolutionary virtual agent (EVA). This new light-weight java-based implementation is based on a dynamical rule-based subsumption architecture, an XML knowledge base and a scheme kernel for scripting behavior rules. Using this architecture, the agent is able to answer questions in natural language while learning a user´s profile. It also extracts relevant information from the Web through search engines queries and use them in the flow of conversation. This paper describes the architecture and analyses its Web mining process.