Mark Curphew in his blog made an interesting post on the dangers posed by online data-mining. The message is that there are people that with just a small amount of information can piece together quite a lot about you by mining. They Google your name combined with anything else they know about you to amass a whole load more information on you.
I wrote something in this area in my first article (Identity Linkage and Privacy) published for the first time in April 2007. Unstructured information that is posted online, may not have a direct link to you (your identity) however a ‘dormant identity link’ can link this data to your identity. i.e. the aggregate of information can link to your identity, but each of these pieces of information by themselves are meaningless.
I suppose the question is ‘why would anyone want to do this’?.
Particularly in the case of Mark, seems like the guy had too much time on his hands. In fact one of the most publicized areas is for the purpose of ‘online grooming’ of children by paedophiles. All of this subject area and more is covered in the book I expect to publish -once I decide who to publish with- in the next month or so. So watch this space 🙂
3 Replies to “Online data mining”
My pleasure 🙂
Thank you very much. I hope I can tell the real story sometime, after I cleared it with Mark and have closed that matter.
Putten, 23rd january 2008
Putten, The Netherlands,
I have nothing too hide. The story is not correct. It took only about 5 minutes to find information on the website and analyzing the info.
Jacob Peter Dokter