A Learning Apprentice For Browsing

This paper describes the task of browsing and an agent we have dev eloped to improve the speed and success rate of browsing. The agent is a learning apprentice: it monitors the user’s normal browsing actions and learns a measure of "relevance" to the user interests. It searches the library being browsed, uses the learned measure to evaluate items and presents to the user those that are most relevant. The paper discusses the main issues raised during the development of the browsing agent. These are of general interest not only because browsing is of considerable practical importance but also because it represents a prototypical task for learning apprentice research.