Spam filters: bayes vs. chi-squared; letters vs. words Export

@inproceedings{obrien03:_spam_filters, abstract = {We compare two statistical methods for identifying spam or junk electronic mail. Spam filters are classifiers which determine whether an email is junk or not. The proliferation of spam email has made electronic filtering vitally important. The magnitude of the problem is discussed. We examine the Naive Bayesian method in relation to the 'Chi by degrees of Freedom' approach, the latter used in the field of authorship identification. Both methods produce very promising results. However, the 'Chi by degrees of Freedom' has the advantage of providing significance measures, which will help to reduce false positives. Statistics based on character-level tokenization proves more effective than word-level.}, author = {O'Brien, Cormac and Vogel, Carl}, booktitle = {ISICT '03: Proceedings of the 1st international symposium on Information and communication technologies}, citeulike-article-id = {682907}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=963600.963658}, keywords = {bayes, machinelearning}, location = {Dublin, Ireland}, pages = {291--296}, posted-at = {2006-06-04 07:21:54}, priority = {2}, publisher = {Trinity College Dublin}, title = {Spam filters: bayes vs. chi-squared; letters vs. words}, url = {http://portal.acm.org/citation.cfm?id=963600.963658}, year = {2003} }

TY - CONF ID - obrien03:_spam_filters L3 - citeulike-article-id:682907 N2 - We compare two statistical methods for identifying spam or junk electronic mail. Spam filters are classifiers which determine whether an email is junk or not. The proliferation of spam email has made electronic filtering vitally important. The magnitude of the problem is discussed. We examine the Naive Bayesian method in relation to the 'Chi by degrees of Freedom' approach, the latter used in the field of authorship identification. Both methods produce very promising results. However, the 'Chi by degrees of Freedom' has the advantage of providing significance measures, which will help to reduce false positives. Statistics based on character-level tokenization proves more effective than word-level. CY - Dublin, Ireland EP - 296 TI - Spam filters: bayes vs. chi-squared; letters vs. words PB - Trinity College Dublin T2 - ISICT '03: Proceedings of the 1st international symposium on Information and communication technologies SP - 291 KW - bayes KW - machinelearning AU - O'Brien, Cormac AU - Vogel, Carl PY - 2003/// UR - http://portal.acm.org/citation.cfm?id=963600.963658 ER -