Online Discriminative Spam Filter Training

We describe a very simple technique for discriminatively training a spam filter. Our results on the TREC Enron spam corpus would have been the best for the Ham at .1% measure, and second best by the 1-ROCA measure. For the Mr. X corpus, our 1-ROCA measure was a close second best, and third best by the Ham at .1% measure. We use a very simple feature extractor (all words in the subject and headers). Our learning algorithm is also very simple: gradient descent of a logistic regression model.

• Type: Conference
• Year: 2006
• Where: CEAS
• Authors: Joshua Goodman, Wen-tau Yih
• Keywords: 1-ROCA Measure, CEAS 2006, Enron Spam Corpus, Internet Technology, Simple Technique