Evaluation and Extension of the AISEC Email Classification System

  • Nrupal Prattipati
  • Emma Hart
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5132)


An existing system - AISEC - which categorises email as interesting or uninteresting using an immune-inspired algorithm is implemented as a plug-in to Outlook to allow seamless user testing. Experiments are performed with a new, large data set to validate previous published results. We show comparable results can be obtained on different data-sets if the system parameters are correctly tuned; the algorithm is particularly sensitive to certain parameters. Some flaws in the original algorithm are identified; a modification is proposed to the learning process of the algorithm and to the mutation operator. Tests with the modified algorithm in a number of scenarios in which users’ interests frequently change show the improved algorithm is capable of continuously adapting to achieve high classification accuracy and can accurately track changes in user interests. The improvements are statistically significant when compared to the original system.


Mutation Operator Markov Chain Model User Feedback Concept Drift User Interest 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    Clarke, E., Hone, A., Timmis, J.: A markov chain model of the b-cell algorithm. In: Jacob, C., Pilat, M.L., Bentley, P.J., Timmis, J.I. (eds.) ICARIS 2005. LNCS, vol. 3627, pp. 318–330. Springer, Heidelberg (2005)Google Scholar
  3. 3.
    Gledhill, C.: Collocations in Science Writing. Gunter Narr Verlag Tübingen, Tübingen (2000)Google Scholar
  4. 4.
    Kelsey, J., Timmis, J.: Immune inspired somatic contiguous hypermutation for function optimisation. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2724. Springer, Heidelberg (2003)Google Scholar
  5. 5.
    Nanas, N., De Roeck, A., Uren, V.: Immune inspired adaptive information filtering. In: Bersini, H., Carneiro, J. (eds.) ICARIS 2006. LNCS, vol. 4163, pp. 418–431. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Oda, T., White, T.: Immunity from spam: an analysis of an artificial immune system for junk email detection. In: Jacob, C., Pilat, M.L., Bentley, P.J., Timmis, J.I. (eds.) ICARIS 2005. LNCS, vol. 3627, pp. 2289–2776. Springer, Heidelberg (2005)Google Scholar
  7. 7.
    Provost, F., Fawcett, T., Kohavi, R.: The case against accuracy estimation for comparing classifiers. In: Proceedings of the Fifteenth International Conference on Machine Learning, ICML 1998 (1998)Google Scholar
  8. 8.
    Secker, A., Freitas, A.A., Timmis, J.: Aisec: an artificial immune system for email classification. In: IEEE Congress on Evolutionary Computation CEC 2003, pp. 131–138 (2003)Google Scholar
  9. 9.
    Sherman, B.: Where do white collar workers actually spend their time in the office (2007),
  10. 10.
    Yue, X., Abraham, A., Chi, Z.-X., Hao, Y.-Y., Mo, H.: Artificial immune system inspired behaviour-based anti-spam filter. Soft Computing - A Fusion of Foundations, Methodologies and Applications 11(8), 729–740 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Nrupal Prattipati
    • 1
  • Emma Hart
    • 1
  1. 1.Napier UniversityScotland

Personalised recommendations