A method for knowledge integration of ontology-based user profiles in personalised document retrieval systems

ABSTRACT

The development of the Internet exceeds the ways to obtain information. Nowadays, a user is overloaded by information from every domain. In our work, we consider a Personalised Document Retrieval System that gathers information about user interests, determines a user profile and helps the user to obtain relevant documents. The scope of the paper is to develop techniques for integrating knowledge about a group of users and determining a profile that represents the group. Such a profile is then used to avoid 'cold-start' problem in a personalisation system. Experimental evaluations were performed to check the effectiveness of the system.

KEYWORDS:

• Ontology-based user profile
• knowledge integration
• Bayesian network
• user profile recommendation
• 'cold-start' problem

Acknowledgments

This research was partially supported by the Polish Ministry of Science and Higher Education.

Disclosure statement

No potential conflict of interest was reported by the author.