User modelling and information filtering for consumer health information

This paper describes an information filtering system that creates personalized web pages with new and relevant information for users. The system maintains a model of each user based on web pages visited and relevance rankings made of those pages made by the user. The system has been used with a consumer health information web site. Focus interviews with test subjects were conducted. Among the most important issues raised by test subjects was a sense of loss of control and privacy. Human factors issues and future implications of intelligent agents in the consumer health care sector are discussed.