One of the ideas for a series that has been floating about in my head for a long time is the idea of fighting spam in foreign languages.
Now, while I am fluent in over six million forms of communication, unfortunately, the foreign languages common to our international customer base is not among them. Thus, foreign languages are my Achilles heel, as it were.
This should not be confused with a weakness in our foreign language spam filtering. Far from it, in fact. We have foreign language analysts who do a great job. Reputation filtering takes out most spam, and foreign language stuff is no different. Rather, foreign languages are my personal Achilles heel.
To that end, I am going to start a series of blog posts on the challenges and idiosyncrasies of fighting spam in foreign languages. What contrasts it from English language spam? How is it encoded? What are the grammatical constructs that we need to watch out for? Does reputation filtering work the same way?
These are the questions that I will seek to answer.
PingBack from http://blog.a-foton.ru/index.php/2009/02/18/spam-filters-and-foreign-spam-part-1/