[Sorry, I've been going through my old email.] > From: http://www.cs..edu/~b > Date: Sun, 18 Nov 2012 09:53:55 -0800 > > So, I got interviewed by the Daily Cal: > > ... and then, today, I got an email from some company that wants to make me > a plaque with the article laminated on it for $200. > > The question is, how did they get from the article to my email address? > It's public information, in the UC directory as well as on my web page, > but presumably this company can't survive on just the Daily Cal; they > probably scrape every newspaper on the web. And they had to figure out > that I'm the UCB Brian and not the dead rock and roller Brian, etc. > > This is the sort of task that's not too hard for a human being to do in > any particular case, but it's kind of scary that they can program computers > to do it in general. > > Our faculty are making a big push in data mining research, so I really > shouldn't be surprised by stuff like this. What blew me away was that, a few months ago, Noelle got an email referencing our web site which (1) did not have her name anywhere on it and (2) did not have her email address. To this day, I still cannot figure out how they found the correlation between the two.