Glen Turpin: The Identity Question » social graph

I’m a geek. See me chart.

Glen — Wed, 17 Jun 2009 02:27:41 +0000

Own your words

Glen — Wed, 15 Apr 2009 12:56:14 +0000

Ars Technica reports that two University of Texas researchers can “de-anonymize” Twitter accounts based on the structure of online social network connections. They point out that “anonymity is not sufficient for privacy.”

Their newest paper, “De-anonymizing social networks,” is yet another attack on the idea that data can be easily anonymized by stripping out a few bits of personally identifiable information (PII). Much of their work over the last few years is built on the premise that PII extends far beyond names and addresses; in many datasets, the very structure of the data provides all sorts of clues that can be deciphered with only a few bits of information.

I confess to only having skimmed the paper , as it’s outside the scope of my geekiness, but the implications are serious.

We show that a third of the users who are verifiable members of both Flickr and Twitter can be recognized in the completely anonymous Twitter graph with only 12% error rate,* even though the overlap in the relationships for these members is less than 15%!

Anonymity isn’t what it used to be. Your words are going to be online for a long time, so choose them wisely.

Notes:

* Granted, a 12% error rate is huge. Think of it as a 88% success rate. Either way, the results are significant.

Who are the real influencers on Twitter?

Glen — Tue, 09 Dec 2008 13:27:02 +0000

A new research paper from HP investigating interactions on Twitter reveals:

…the driver of [Twitter] usage is a sparse and hidden network of connections underlying the “declared” set of friends and followers.

The Social Computing Lab at HP analyzed usage patterns of more than 300,000 Twitter users. Their initial conjecture was that people who receive a lot of attention on a social network pose more often than those who receive little attention. But they determined that the number of friends a user has is a more accurate signal of activity than the number of followers.*

Twitter users have a very small number of friends compared to the number of followers and followees they declare. This implies this existence of two different networks: a very dense one made up of followers and followees, and a sparser and simpler network of actual friends. This latter proves to be a more influential network in driving Twitter usage since users with many actual friends tend to post more updates that users with few actual friends.

Word of mouth is driven by the hidden social network. How do you find it?

Notes:

* The study defines a “friend” as someone to whom the user has directed at least two @replies.