Filtering Email Spam in the Presence of Noisy User Feedback

  title={Filtering Email Spam in the Presence of Noisy User Feedback},
  author={D. Sculley and Gordon V. Cormack},
Recent email spam filtering evaluations, such as those conducted at TREC, have shown that near-perfect filtering results are attained with a variety of machine learning methods when filters are given perfectly accurate labeling feedback for training. Yet in realworld settings, labeling feedback may be far from perfect. Real users give feedback that is often mistaken, inconsistent, or even maliciously inaccurate. To our knowledge, the impact of this noisy labeling feedback on current spam… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS
23 Citations
27 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 27 references

TREC 2006 spam track overview

  • G. V. Cormack
  • In TREC 2006: Proceedings of the Fifteenth Text…
  • 2006
Highly Influential
4 Excerpts

Generative and discriminative classifiers: Naive bayes and logistic regression

  • T. M. Mitchell
  • In Machine Learning.∼tom…
  • 2005
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…