BT Technology Journal

, Volume 16, Issue 3, pp 110–117 | Cite as

Automatic Learning of User Profiles — Towards the Personalisation of Agent Services

  • S. J. Soltysiak
  • I. B. Crabtree
Article

Abstract

Agent technology is able to provide increasingly more services for individuals, groups and organisations. Services such as information finding, filtering and presentation, service/contract negotiation, and electronic commerce are now possible. User profiling is fundamental to the personalisation of this technology. This paper describes experimental work conducted to investigate user profiling within a framework for personal agents. In particular investigations were aimed at discovering whether user interests could be automatically classified through the use of several heuristics. The results highlighted the need for minimal user feedback, and the need to consider the implications for the role of machine learning in user profiling.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Nwana H S: 'Software agents: an overview', The Knowledge Engineering Review, 11, pp 144—205 (1996).Google Scholar
  2. 2.
    Moukas A: 'User modelling in a multiagent evolving system', Proceedings of the Workshop on Machine Learning for User Modeling, 6th International Conference on User Modeling, Chia Laguna, Sardinia (1997).Google Scholar
  3. 3.
    Davies N J and Weeks R: 'ProSum — profile-based text summarisation', First Automatic Text Summarisation Conference (SUMMAC-1), Virginia, USA (May 1998).Google Scholar
  4. 4.
    Fisk D: 'An application of social filtering to movie recommendation', BT Technol J, 14, No4, pp 124—132 (1996).Google Scholar
  5. 5.
    Foner L: 'A multi-agent referral system for matchmaking', Proceedings First International Conference on the Practical Applications of Agents and Multi-Agent Systems, London, UK (1996).Google Scholar
  6. 6.
    Foner L and Crabtree I B: 'Multi-agent matching', BT Technol J, 14, No4, pp 115—123 (1996).Google Scholar
  7. 7.
    Dunn M, Gwertzann J, Layman A and Partovi H: 'Privacy and profiling on the Web', Technical Note, w3c, available as http:// www.w3.org/TR/NOTE-Web-privacy.html (1997).Google Scholar
  8. 8.
    Hensley P, Metral M, Shardanand U, Converse D and Myers M: 'Proposal for an open profiling standard', Technical Note, w3c, available as http://www.w3.org/TR/NOTE-OPS-FrameWork.html (1997).Google Scholar
  9. 9.
    Soltysiak S J and Crabtree I B: 'Knowing me, knowing you: practical issues in the personalisation of agent technology', Proceedings of the 3rd International Conference on the Practical Application of Agents and Multi-Agent Technology (PAAM 98), London, UK (1998).Google Scholar
  10. 10.
    Pazzam M J and Billsus D: 'Learning and revising user profiles: The identification of interesting Web Sites', Machine Learning, 27, No3 (1997).Google Scholar
  11. 11.
    Salton G and Buckley G: 'Term-weighting approaches in automatic text retrieval', Information Processing and Management, 24, pp 513— 523 (1988).Google Scholar
  12. 12.
    Crabtree I B and Soltysiak S J: 'Identifying and tracking changing interests', in Ferguson I (Ed): 'Working notes of the IJCAI workshop on the integration of artificial intelligence and digital libraries: moving from chaos to (more) order', Nagoya, Japan (August 1997).Google Scholar
  13. 13.
    Davies N J and Crabtree I B: 'ProSum and user profiling', Internal Technical Report, BT Laboratories (February 1998).Google Scholar
  14. 14.
    Deerwester S, Dumais S T and Furnas G W: 'Indexing by latent semantic analysis', Journal of the American Society for Information Science, 41, pp 391—407 (1990).Google Scholar
  15. 15.
    Miller G: 'WordNet: an on-line lexical database for English', International Journal of Lexicography, 3, No4 (1991).Google Scholar

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • S. J. Soltysiak
  • I. B. Crabtree

There are no affiliations available

Personalised recommendations