Friday, January 08, 2010

Facebook Research

Day-of-the-week effects have been mentioned on the blog before, including research by Gerard O Neill from Amarach Consulting. A recent article in the New York Times reports that "there is a 9.7 percent increase in happiness on Fridays compared with the worst day of the week, Monday. That is among the discoveries made by Facebook researchers with access to two years of anonymous “status updates” from 100 million users in the United States."

The Facebook Global Happinness Index (from is shown below. The Facebook Research page related to this index is available here. The Happiness Index is based on the Linguistic Inquiry and Word Count (LIWC).

Updates from Facebook's data-team can be accessed here. The Top 15 status terms of 2009 can be viewed here. Analysis of maintained relationships on Facebook can be viewed here. With more data than ever available through the rise of Web 2.0, the Flowing Data blog suggests that we may see the rise of the "data-scientist".


Liam Delaney said...

fascinating martin. linking this type of data with daily survey work coming from gallup and others will yield some really interesting stuff in the years to come.

Kevin Denny said...

People are happier on Thanksgiving? Whoop-di-do. The bogus cardinality that has slipped in here "a 9.7% increase in happiness" is annoying enough and something that should be immediately corrected by economists.
That aside, I wonder what data-scientists are? I have been working with data all my career as have many others in diverse areas.
What is happening is that the internet is spewing out lots of information (via Facebook, Google, Twatter etc) and some people want to jump on the bandwagon. Thats ok, but zillions of datapoints are not enough, you need good ideas (& good training, of course) and one has to be careful about what the data can actually tell you.
At the moment there is a bit of a lag in the process: maybe something scientifically interesting will turn up in years to come. But we have a long way to go.

Liam Delaney said...

I think the lag is in publishing and distributing Kevin. I have seen very sophisticated stuff but a lot of people mining this type of data are doing it to make money not to publish it. I think some of these guys are getting close to replicating what you would get from daily surveys and that would be scientifically very valuable.

Martin Ryan said...


It appears that Twatter is a real alternative to Twitter. ;)

Interestingly, it runs the StatusNet microblogging software, version 0.8.2, available under the GNU Affero General Public Licence.

I wonder if this means it would not be too difficult to set up a competitor to Twitter/Twatter. Presumably there is a lot of value in the Twitter brand.

One of the most interesting things I have seen done with web-data is Yahoo! Research measuring the effects of advertising on sales through a controlled experiment.

The research made use of a database match between Yahoo! and a nationwide retailer by identifying users who registered the same email address with both companies. After finding over one million matched users, the researchers randomly assigned them to treatment and control groups for one of the retailer’s online advertising campaigns.

The project then tracked sales each week at the retailer, both online and in stores. The researchers found that online display advertising increased total revenues by approximately 5% for those users exposed to the ads, with 93% of the total effect happening in offline sales. They also observed online ads to have a large impact on sales even when the ads are not clicked: 78% of the increase in sales came from those who viewed, but did not click, the ads. This has massive implications for the "pay-per-click" model in online advertising.

A set of relevant links are available in this blog post from earlier this year:

Kevin Denny said...

Liam: I look forward to seeing some interesting hypotheses tested.
Martin: I didn't know that. The twats seemed about as interesting as the twits - or is tweets?
I wonder how these things translate into the first national language, lacking a w?
I am currently beta-testing my own version of micro-blogging. Its called Nutter. It involves saying something completely daft in 140 characters. Actually sounds a bit like...