The article describes a content personalization system that uses learned user profiles to target appropriate content items for individual end users, with specific focus to a fully deployed personalized Internet service called Personalized Television. This service performs personalized television (TV) listings content to over 20,000 users in Ireland and Great Britain. It employs a system known as ClixSmart, where actions of individual users are stored as they select, browse and read content assets, and this information is used to infer interest in specific content assets stored in the content database. ClixSmart personalization manager employs two filtering strategies, content-based filtering approach and collaborative filtering techniques. Similarly, PTV, an Internet system offering personalized information service for television viewers, uses the ClixSmart personalization engine to generate electronic TV guides personalized for the viewing preferences of individual users.

This article reports on the Universal Law of Web Surfing, which maintains that Web surfing patterns for users are quite regular, manifesting a preference for shorter surfing sessions over longer ones. The authors assess whether these regularities apply to surfing on the mobile Web, specifically through Wireless Application Protocol (WAP) portals, where many aspects of the user environment are quite different from the conventional Web. The article analyzes a large sample of mobile Web user data.