Joint NLP Lab between HIT 2 at CEAS Spam-filter Challenge 2008

Abstract

This paper reports our participation of CEAS Spam-filter Challenge 2008. The logistic regression model, n-gram and TONE (Train On /Near Error) were used to build the systems. We improved the weighting method which reduces the impact of the features appearing both in spam messages and ham messages. . We achieved competitive results in all tasks and got the first in a subtask of Lab Evaluation Task.