A SOFTWARE AGENT FOR CONTENT BASED RECOMMENDATIONS FOR THE WWW

Gulden Uchyigit

2008

Abstract

The evolution of the WWW has led to an explosion of information and consequentially a significant increase on usage. This avalanche effect has resulted in such uncertain environment in which we find it difficult to clarify what we want, or to find what we need. In this paper we introduce RecSys which aims to confront the problem by developing a software agent which intelligently learns users interests, and hence makes recommendations of resources on WWW based on the user’s profile. The system employs multiple TFIDF vectors to represent various domains of user’s interests. It continuously and progressively learns users profile from both implicit and explicit feedback. This is achieved by extraction and refinement of featured keywords within the learning examples. Several heuristics were also adapted to improve the overall performance of the system.

References

  1. Chen, L. and Sycara, K. (1998). Webmate: A personal agent for browsing and searching. In 2nd International Conference on Autonomous Agents, Minneapolis MN USA.
  2. Mladenic, D. (1996). Personal webwatcher: design and implementation. Technical report, Department for Intelligent Systems, J. Stefan Institute, Jamova 39, 11000 Ljiubjana, Slovenia.
  3. Lang, K. (1995). Newsweeder: Learning to filter netnews. In 12th International Conference on Machine Learning.
  4. Moukas, A. (1996). Amalthaea: Information discovery and filtering using a multi-agent evolving ecosystem. In Proc. 1st Intl. Conf. on the Practical Application of Intelligent Agents and Multi Agent Technology, London.
  5. Liberman, H. (1995). Letzia: An agent that assists in web browsing. In Proceedings of the 1995 International Joint Conference on Artificial Intelligence, Montreal, Canada.
  6. Armstrong, R., Freitag, D., Joachims, T., and Mitchel, T. Webwatcher: A learning apprentice for the world wide web. In AAAI Spring Synopsium on Information Gathering from Heterogenous, Distributed Environments. (1995)
  7. Baeza-Yates, R. and Ribeiro-Neto, B. (1999). Modern Information Retrieval. Adsison Wesley.
  8. Balabanovic, M. (1998). Learning to Surf: Multi-agent Systems for Adaptive Web Page Recommendation. PhD thesis, Department of Computer Science, Stanford University.
  9. Pazzani, M. and Billsus, D. (1997). Learning and revising user profiles: The identification of interesting web sites. Machine Learning, 27:313-331.
Download


Paper Citation


in Harvard Style

Uchyigit G. (2008). A SOFTWARE AGENT FOR CONTENT BASED RECOMMENDATIONS FOR THE WWW . In Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: ICEIS, ISBN 978-989-8111-39-5, pages 178-183. DOI: 10.5220/0001720501780183


in Bibtex Style

@conference{iceis08,
author={Gulden Uchyigit},
title={A SOFTWARE AGENT FOR CONTENT BASED RECOMMENDATIONS FOR THE WWW},
booktitle={Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: ICEIS,},
year={2008},
pages={178-183},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001720501780183},
isbn={978-989-8111-39-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: ICEIS,
TI - A SOFTWARE AGENT FOR CONTENT BASED RECOMMENDATIONS FOR THE WWW
SN - 978-989-8111-39-5
AU - Uchyigit G.
PY - 2008
SP - 178
EP - 183
DO - 10.5220/0001720501780183