It appears to me that spam systems work out the probability that some item of mail is spam based on some sort of algorithms.<p>However, recently I have been processing hundreds of thousands of emails including hundreds of thousands of items of spam.<p>I can see in the spam emails that there are many words and phrases used in the subject lines that will simply never appear in any valid email that I care about receiving. For example:<p>H00kup<p>F*ckbuddy<p>Xenical<p>Viagra<p>BangBuddy<p>In addition to the single words, there are various phrases in the subject lines that would never appear in a legit email, such as:<p>Affordable lux Copy watches<p>accessories for cheap<p>Designer timepieces for all tastes<p>Time to look rich<p>So it strikes me that maybe there is a list of words and phrases that, if found in an email subject line, definitely identify that email as spam.<p>Does anyone know if such a list exists? A list of words/phrases that would only ever be found on a spam email?
I came across this 'STOP words' <a href="https://en.wikipedia.org/wiki/Stop_words" rel="nofollow">https://en.wikipedia.org/wiki/Stop_words</a> yesterday. Wiki says these word list can vary from services to services. There is hardly any chance you'll find a complete list, maybe common words are available.