In recent years, it has become increasingly difficult for users to find relevant information within the accessible glut. Adaptive Information Filtering (AIF) tackles this problem through a tailored representation of the user interests, called "user profile". The user profile must be able to represent the user's multiple topics of interest and adapt to various changes in them.

With our experimental system 'Nootropia', we achieve adaptive document filtering with a single, multi-topic user profile. A hierarchical term network that takes into account topical and lexical correlations between terms and identifies topic-subtopic relations between them, is used to represent a user's multiple interests and distinguish between them. A series of non-linear document evaluation functions is then established on the hierarchical network. Adaptation is then achieved through a process of self-organisation that constantly readjusts the profile stucturally, in response to user feedback. The approach has been tested experimentally with positive results. Furthemore, Nootropia may support additional personalisation services like automatic query formulation and expert finding, or can be applied in combination with collaborative filtering. It is also interesting that, in principle, the approach can be applied to other media like audio and image for which features can be automatically extracted.

Download PowerPoint Presentation (1Mb ZIP file)

Watch the webcast replay >>