Exploiting Learning Technologies for World Wide Web Agents

This paper illustrates how machine learning techniques can be utilised within intelligent software agents which assist users with the management of Web-based information. We discuss a number of recent activities within the Learning Agents & Systems 1 group at Aberdeen, namely: a generic Web browsing assistant; an agent which constructs personalised travel brochures; the application of clustering techniques to Web browser histories; and multi-agent support for adaptive user querying. 1 Introduction The recent, rapid growth of the World Wide Web has led to enormous amounts of on-line information. However, as the volume of this information has increased, so have the problems encountered by users in dealing with it. Interface agents have been proposed as one solution to this problem and can be characterised as systems which "employ Artificial Intelligence techniques to provide assistance to users dealing with a particular computer application" [1]. In order to be able to assist the user..