Facebook 'likes' serve as personality test

CNN video: Study: Facebook 'likes' serve as personality test (watch below).

The research done by a team at Cambridge University was published in PNAS a year ago. There are new tools now that can help guard your privacy (see the end of this post), hence the reason for linking to this.

Surprisingly accurate estimates of Facebook users’ race, age, IQ, sexuality, personality, substance use and political views can be inferred from automated analysis of Facebook Likes - information currently publicly available by default.

Statistical models proved 85% accurate differentiating Republican from Democrat. Good prediction accuracy was achieved for relationship status and substance abuse – between 65 and 73%. But few users clicked Likes explicitly revealing these attributes. Accurate predictions relied on ‘inference’ - aggregating huge amounts of less informative but more popular Likes such as music and TV shows to produce incisive personal profiles.

Even seemingly opaque personal details such as whether users’ parents separated before the user reached the age of 21 were accurate to 60%, enough to make the information “worthwhile for advertisers”, suggest the researchers.



One of the study authors added: “I have used Facebook since 2005, and I will continue to do so. But I might be more careful to use the privacy settings that Facebook provides.”

Here is what you can do now.

The recommendation is based on a recent WSJ article: People Battle to Regain Online Privacy: 86% have taken steps to mask their digital footprints http://buff.ly/1lxbUxR.

One of the apps, AVG PrivacyFix, is a free download for Chrome and works well. Give it a try: http://www.avg.com/us-en/privacyfix

References:

Private traits and attributes are predictable from digital records of human behavior. PNAS, 2013.

Digital records could expose intimate details and personality traits of millions | University of Cambridge http://buff.ly/1hRVdGP

Facebook 'likes' can reveal your secrets, study finds http://buff.ly/1dGK0NI

No comments:

Post a Comment

Blog Widget by LinkWithin