The huge production of multimedia information available on the World Wide Web stimulates the development of fast and effective systems that support an easy access to the information items relevant to specific users’ needs. The definition and development of systems that help users in accessing multimedia information relevant to their needs is a very important research topic. The activity of these systems is based on the solution of a decision-making problem: how to identify the information items that correspond to the users’ information preferences?

The PENG project focuses on the problem of defining a news content composition and programming environment to the aim of offering to professional and general users an interactive and personalised tool for multimedia news gathering and delivery.

The system which is proposed within the PENG project aims in fact at collecting news from specialised archives in a personalised way, making the user able to deepen a selected topic by searching for additional information on the specialised archives, the web and personal archives, and editing the final news through a multi-document summarisation approach. This means both personalising the collection of news concerning an interesting topic and providing automatic support for expanding or summarising the more relevant retrieved documents, for the aim of selecting the salient features of information the user is looking for. In particular the automatic editing phase can be seen as a first but very important support to a journalist's activity.

Categories of users are mainly addressed by this project according to a bi-dimensional classification schema defined in terms of their level of interest in the news and their topical interest. Possible user targets could be information-intensive workers, students of communication faculties, journalists interested in sport, culture, economy, etc. An important characteristic that will be ensured by the system will be the flexibility in modelling the user topical interests and context, intended as the capability to be both tolerant to the vagueness and uncertainty in the user-system interaction and adaptive in the learning process of users' preferences changing over time.