This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Experience with Rule Induction and k-Nearest Neighbor Methods for Interface Agents that Learn
March-April 1997 (vol. 9 no. 2)
pp. 329-335

Abstract—Interface agents are being developed to assist users with a variety of tasks. To perform effectively, such agents need knowledge of user preferences. An agent architecture has been developed which observes a user performing tasks, and identifies features which can be used as training data by a learning algorithm. Using the learned profile, an agent can give advice to the user on dealing with new situations. The architecture has been applied to two different information filtering domains: classifying incoming mail messages (Magi) and identifying interesting USENet news articles (UNA). This paper describes the architecture and examines the results of experimentation with different learning algorithms and different feature extraction strategies within these domains.

[1] B.D. Sheth, "A Learning Approach to Personalized Information Filtering," master's thesis, Dept. of Electrical Engineering and Computer Science, Massachusetts Inst. of Tech nology, 1994.
[2] T.R. Payne, "Learning Email Filtering Rules with Magi, A Mail Agent Interface," master's thesis, Dept. of Computing Science, Univ. of Aberdeen, Scotland, 1994.
[3] T. Mitchell et al., "Experience with a Learning Personal Assistant," Comm. ACM, Vol. 37, No. 7, July 1994, pp. 80-91.
[4] R. Kozierok and P. Maes, "A Learning Interface Agent for Scheduling Meetings," Proc. ACM-SIGCHI Int'l Workshop Intelligent User Interfaces, ACM Press, New York, pp. 81-88, 1993.
[5] T.W. Malone et al., "Intelligent Information-Sharing Systems," Comm. ACM, Vol. 30, No. 5, May 1987, pp. 390-402.
[6] D.N. Chin, "Intelligent Interfaces as Agents," Intelligent User Interfaces, J.W. Sullivan and S.W. Tyler, eds., ACM Press, New York, pp. 177-206, 1991.
[7] Y. Gil, "Trainable Software Agents," Software Agents: Papers from 1994 Spring Symp.,Menlo Park, Calif., AAAI, pp. 99-102, 1994.
[8] K. Lang, "NewsWeeder: Learning to Filter Netnews," Proc. 12th Int'l Machine Learning Conference (ML95), Morgan Kaufmann, San Francisco, pp. 331-339, 1995.
[9] G. Salton and M. McGill, Introduction to Modern Information Retrieval, McGraw Hill, New York, 1983.
[10] M.E. Metral, "Design of a Generic Learning Interface Agent," BSc thesis, Dept. of Electrical Engineering and Computer Science, Massachusetts Inst. of Tech nology, 1993.
[11] C. Stanfill and D. Waltz, “Toward Memory-Based Reasoning,” Comm. ACM, vol. 29, pp. 1213-1228, 1986.
[12] R. Armstrong, D. Freitag, T. Joachims, and T. Mitchell, "Web-Watcher: A Learning Apprentice for the World Wide Web," Working Notes AAAI Spring Symp. Information Gathering from Distributed, Heterogeneous Environments,Menlo Park, Calif., AAAI, 1995, http://www.isi.edu/sims/knoblock/sss95/info-gathering.html.
[13] T.R. Payne and P. Edwards, "Interface Agents that Learn: An Investigation of Learning Issues in a Mail Agent Interface," Applied Artificial Intelligence J., vol. 11, no. 1, pp. 1-32, 1997.
[14] P. Clark and T. Niblett, "The CN2 Induction Algorithm," Machine Learning, vol. 3, pp. 261-283, 1989.
[15] B.V. Dasarathy, Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques.Los Alamitos, Calif.: IEEE CS Press, 1991.
[16] C.L. Green, "USENet News Agent," BSc final year project report, Dept. of Computing Science, Univ. of Aberdeen, Scotland, 1995.
[17] T.M. Cover, "Estimation by the Nearest Neighbor Rule," IEEE Trans. Inform. Theory, vol. 14, pp. 50-55, 1968.
[18] S. Cost and S. Salzberg, "A Weighted Nearest Neighbor Algorithm for Learning with Symbolic Features," Machine Learning, Vol. 10, No. 1, Jan. 1993, pp. 57-78.
[19] P. Domingos and M. Pazzani, "Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier," Proc. 13th Int'l Machine Learning Conf. (ICML96), Morgan Kaufmann, San Francisco, pp. 105-112, 1996.
[20] J. Rachlin, S. Kasif, S. Salzberg, and D.W. Aha, "Towards a Better Understanding of Memory-Based Reasoning Systems," Proc. 11th Int'l Machine Learning Conf. (ML94), Morgan Kaufmann, San Francisco, pp. 242-250, 1994.
[21] P. Clark, "A Comparison of Rule and Exemplar-Based Learning Systems," Machine Learning, Meta-Reasoning, and Logics, P.B. Brazdil and K. Konolige, eds., Kluwer, Boston, pp. 159-186, 1990.

Index Terms:
Machine learning, interface agent, information filtering, intelligent USENet news reader, intelligent e-mail filter, agent architecture, instance-based learning, rule induction.
Citation:
Terry R. Payne, Peter Edwards, Claire L. Green, "Experience with Rule Induction and k-Nearest Neighbor Methods for Interface Agents that Learn," IEEE Transactions on Knowledge and Data Engineering, vol. 9, no. 2, pp. 329-335, March-April 1997, doi:10.1109/69.591456
Usage of this product signifies your acceptance of the Terms of Use.