Toward an ontology-enhanced information filtering agent

ABSTRACT

Whereas search engines assist users in locating initial information sources, often an overwhelmingly large number of ULRs is returned, and the task of browsing websites rests heavily on users. The contribution of this work is developing an information filtering agent (IFA) that assists users in identifying out-of-context web pages and rating the relevance of web pages. An IFA determines the relevance of web pages by adopting three heuristics: (i) detecting evidence phrases (EP) constructed from WORDNET's ontology, (ii) counting the frequencies of EP and (iii) considering the nearness among keywords. Favorable experimental results show that the IFA's ratings of web pages are generally close to human ratings in many instances. The strength and weaknesses of the IFA are also discussed.

REFERENCES

• 1: G. A. Miller. WORDNET: An On-line Lexical Database. International Journal of Lexicography 3-4, pages 235--312.
• 2: Gerald Salton, Automatic text processing, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1988
• 3: F. Parker & K. Riley. Linguistics for Non-Linguists: A Primer with Exercises, (3rd ed.), Allyn & Bacon, 2000.
• 4: Kwang Mong Sim, Web Agents With A Three-Stage Information Filtering Approach, Proceedings of the 2003 International Conference on Cyberworlds, p.266, December 03-05, 2003
• 5: D. Ellis. Modeling the Information Seeking Patterns of Engineers and Research Scientists in an Industrial Environment. Journal of Documentation, 53(4):384--403, 1997.
• 6: D. Sullivan. How Search Engines Rank Web Pages. http://www.searchenginewatch.com/webmasters/rank.html.
• 7: D. L. McGuinness. Ontological Issues for Knowledge-Enhanced Search. In Proc. of Formal Ontology in Information Systems, pp. 302--316, 1998.
• 8: Nicola Guarino , Claudio Masolo , Guido Vetere, OntoSeek: Content-Based Access to the Web, IEEE Intelligent Systems, v.14 n.3, p.70-80, May 1999 [doi>10.1109/5254.769887]
• 9: T. Berners-Lee et. al. The Semantic Web. In a feature article in Scientific American, May 2001.
• 10: Sean Luke , Lee Spector , David Rager , James Hendler, Ontology-based Web agents, Proceedings of the first international conference on Autonomous agents, p.59-66, February 05-08, 1997, Marina del Rey, California, United States [doi>10.1145/267658.267668]
• 11: J. Heflin et. Al (1999). Applying Ontology to the Web: A Case Study. In: J. Mira, J. Sanchez-Andres (Eds.), Proc. Int. Work-Conference on Artificial and Natural Neural Networks, Vol. II. Springer, Berlin, 1999, pp. 715--724.
• 12: J. Abasolo and M. Gómez. MELISA: An ontology-based agent for information retrieval in medicine. ECDL 2000 Workshop on the Semantic Web Lisbon, Portugal. Sep., 2000.