Refereed full papers (journals, book chapters, international conferences)

1998

@inproceedings{SDH1998,
	vgclass =	{refpap},
	author =	{Mehran Sahami and Susan Dumais and David Heckerman and Eric Horvitz},
	title =	{A Bayesian Approach to Filtering Junk E-mail},
	booktitle =	{AAAI Workshop on Learning for Text Categorization},
	address =	{Madison, Wisconsin},
	month =	{July},
	year =	{1998},
	url =	{http://research.microsoft.com/\~{}horvitz/junkfilter.htm},
	abstract =	{In addressing the growing problem of junk email on the
	Internet, we examine methods for the automated construction of filters
	to eliminate such unwanted messages from a user's mail stream. By
	casting this problem in a decision theoretic framework, we are able to
	make use of probabilistic learning methods in conjunction with a notion
	of differential misclassification cost to produce filters which are
	especially appropriate for the nuances of this task. While this may
	appear, at first, to be a straightforward text classification problem,
	we show that by considering domain-specic features of this problem, in
	addition to the raw text of E-mail messages, we can produce much more
	accurate filters. Finally, we show the efficacy of such filters in a
	real world usage scenario, arguing that this technology is mature
	enough for deployment.},
}