An experimental comparison of naive bayesian and keyword based
- 1. An Experimental Comparison of Naive Bayesian and Keyword-Based Anti-Spam Filtering with Personal E-mail Messages Author: Ion Androutsopoulos , John Koutsias ,Konstantinos V. Chandrinos, Constantine D. Spyropoulos Resourse: sigir2000
- 2. Outline Introduction Feature selection The Naive Bayesian classifier Result
- 3. Introduction 垃圾郵件很多 Naïve Bayesian classifier 與 keywork-based 的反垃圾郵件機制做比較 . Sahami et al. trained a Naïve Bayesian classifier on manually categorized legitimate and spare messages
- 4. The Naive Bayesian classifier x = (x l , x 2 , x 3 .... , x n ) , where x l ,….., x n are the values of attributes X 1 .... , X n . Each attribute shows whether or not a particular word (eg. "adult") is present in the message. Use additional attributes corresponding to phrases(e.g. "be over 21") . Non-textual properties (e.g. whether or not the message contains attachments).
- 5. mutual information Use mutual information ( MI ) to select possible attributes. MI(X;C): Then select the attributes with the highest mutual information values.
- 6. The Naive Bayesian classifier
- 9. S -> L (legitimate to spam) L->S(spam to legitimate) denote the two error types. we assume that L->S is times more costly than S -> L Classify a message as spare if the following classification criterion is met:
- 11. = 999 (t=0.999) , This means that mistakenly blocking a legitimate message was taken to be as bad as letting 999 spare messages pass the filter. = 9 (t=0.9) , 若郵件被 blocked 時 , 回傳給 sender 道歉訊息以及猜謎 . = 1(t=0.5), If the recipient does not care about the extra work imposed on the sender.
- 12. Result
- 13. 1789 messages, consisting of 211 legitimate messages that users had saved and 1578 spare messages. First experiment word-attributes were used. Candidate attributes were added (e.g. corresponding to the phrases "be over 21", "only $"). Third experiment, (e.g. whether or not the message contains attachments, or a high proportion of non alphanumeric characters).
- 14. Experiments with the PU1 corpus 481 spam messages. 618 legitimate messages. Naive Bayesian classifier, ten-fold cross validation to reduce random variation. That Results were then averaged over the ten runs. varied the number of retained attributes from 50 to 700 by a step of 50 lemmatizer and stop-list