Hypertext Browsing: A New Model for Information Filtering Based on User Profiles and Data Clustering

Abstract

Hypertext users often experience the ‘lost in hyperspace’ problem. This study suggests a solution which restricts the amount of information made available to the user, thus allowing improved hypertext browsing. An algorithm calculates the set of most relevant hypertext nodes for the user, utilising the user profile and data clustering technique. The result is an optimal cluster of relevant data items, custom‐tailored for each user's needs.