KDnuggets : News : 2002 : n22 : item1 next >


From: Gregory Piatetsky-Shapiro
Date: Nov 18, 2002
Subject: Dealing with junk email

Many people have responded with their suggestions on how to deal with junk email. Many solutions involve the use of complex filters that check for typical sp^m phrases. However, be wary of overzealous filters that can throw away good email like this one because it contains the bad words, like fr*e or sp^m.

Many people who have their email address posted on a web site are bombarded by junk emailers who scoop email addresses from the web.

Mihael Ankerst points to SIGKDD website approach (see http://www.acm.org/sigkdd/contact.html) which gives contact address as infodir_sigkdd_nospam@acm.org, and asks users to manually remove "_nosp^m" from the email address. Other approaches involve using @ instead of @ or javascript to generate email address (see www.kdnuggets.com/news/2002/n21/2i.html).

Some people suggest not to reply to a sp^m message, because the sp^mmers will collect your email address. While indeed some legitimate email marketers do track email response, most sp^mmers do not bother with it.

In my recent experience, most sp^mmers send only one or two emails and then change their address or site, so in most cases it does not matter whether you reply or not. They already have your email and rarely bother to process a remove request. If the sp^m offers only email to ask for removal, I don't bother to reply. Some sp^m offers removal via a website which appears to confirm your removal. As an experiment, I unsubscribed myself from such sp^m for a month, and in most cases I indeed stopped receiving spam from these sites. However, I continue to receive similar junk emails from other sites, so the amount of junk email did not measurably decrease.

Here are some useful tools and articles:

  • Patricia Dowd recommends Mail Washer (www.mailwasher.net), which reduced spam by at least 40% for her. It's either free or you contribute what you wish.

  • www.SpamAssassin.org, a rule-based mail filter to identify sp^m. Works with Unix systems, Outlook, Exchange, and Eudora.

  • Razor (http://razor.sourceforge.net).
    Vipul's Razor is a collaborative spam-tracking database, which works by taking a signature of spam messages. Since spam typically operates by sending an identical message to hundreds of people, Razor short-circuits this by allowing the first person to receive a spam to add it to the database -- at which point everyone else will automatically block it.
    See article from imakenews.

  • Tim Gross, Spam Filters Run-Amuck: Is Your Message Getting Through? Internet Profit Systems. Includes word lists for McAfee Spam Filter (www.iprofitsystems.com/articles/spamfilters.html).

  • Debbie Weil, Clip and Save guide to avoiding sp^m filters, WordBiz Report, 9/25/02. Includes some comments on SpamAssassin as well as many helpful links (www.imakenews.com/wordbiz/e_article000094161.cfm).

KDnuggets : News : 2002 : n22 : item1    ( next)

Copyright © 2002 KDnuggets.   Subscribe to KDnuggets News!