Item Summarization in Personalisation of News Delivery Systems

The designer of an information filtering system based on user preferences formulated as user models has to decide what method to use to provide summaries of the available documents without losing information that may be significant to a particular user even if it would not be considered as such in general terms. In this paper we describe a personalised summarization facility to maximise the density of relevance of information sent by the system. The selection uses a relevance feedback mechanism that captures short term interests as indicated by a user's acceptance or rejection of the news items received. Controlled experiments were carried out with a group of users and satisfactory and insightful results were obtained, providing material for further development. The experimental results suggest that personalised summaries perform better than generic summaries at least in terms of identifying documents that satisfy user preferences.