反垃圾電郵技術

反垃圾電郵技術（英文：anti-spam）係指一部電腦做出「攞一封電郵做 input，output 俾出「封電郵係咪垃圾電郵」」。

反垃圾電郵技術可以想像成簡單嘅監督式學習，研究者可以俾隻 NLP 程式睇一大拃嘅正常電郵（0）同垃圾電郵（1），然後叫隻程式分析兩種電郵有咩分別－例如垃圾電郵好多時都係廣告，會成日出現「你可以買」或者「快啲去買」等嘅字詞，而且喺英文等嘅多種語文入面垃圾電郵亦成日會有成句都大階噉嘅情況，於是研究者可以用 n-gram 嚟分析兩種電郵，教隻程式計 $\Pr($ 封電郵係垃圾 $|$ 封電郵入面出現咗「快啲去買」 $)$ 等嘅好多個機率－最後決定 $\Pr($ 封電郵係垃圾 $)$ 同 $\Pr($ 封電郵唔係垃圾 $)$ 邊個數值大啲^[1]^[2]。

睇埋

參攷

↑ Xie, S., Wang, G., Lin, S., & Yu, P. S. (2012, August). Review spam detection via temporal pattern discovery. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 823-831).
↑ Firte, L., Lemnaru, C., & Potolea, R. (2010, August). Spam detection filter using KNN algorithm and resampling. In Proceedings of the 2010 IEEE 6th international conference on intelligent computer communication and processing (pp. 27-33). IEEE.

呢篇反垃圾電郵技術係關於互聯網嘅楔位文章，重未寫完嘅。麻煩你幫手充實佢。

[1] Xie, S., Wang, G., Lin, S., & Yu, P. S. (2012, August). Review spam detection via temporal pattern discovery. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 823-831).

[2] Firte, L., Lemnaru, C., & Potolea, R. (2010, August). Spam detection filter using KNN algorithm and resampling. In Proceedings of the 2010 IEEE 6th international conference on intelligent computer communication and processing (pp. 27-33). IEEE.

[1]

[2]