Scott Golder and Michael Macy from Cornell University, don’t just use Twitter to follow friends, blogs, or the news. They used Twitter to follow global shifts in mood by analyzing half a billion tweets from 2.4 million people in 84 different countries.
Unlike other similar studies examining mood (that traditionally utilize lots of college students as their subjects), Golder & Macy’s study had a huge, diverse pool of ‘participants’ (though limited to people on Twitter) that they didn’t have to compensate with class credit. The results revealed the peaks times of day and times of the year that people are most positive, and when they’re feeling really negative.
From Discover Magazine:
“They found that, on average, people wake up in a good mood, which falls away over the course of the day. Positive feelings peak early in the morning and again nearer midnight, while negative feelings peak between 9pm and 3am. Unsurprisingly, people get happier as the week goes on.”
Why I’m Curious
I’m really interested in the how obsessive tweeting, Facebooking, and blogging is leaving behind a very detailed collection of data (and if Facebook has its way with the timeline, it’s only going to get more detailed). Sure this information can be used to target ads to users, but it’s also a veritable time capsule of information about everyone tweeting preserved perfectly on the the Internet (which is probably why Library of Congress is keeping an archive of it). The analysis of the tweets also used slightly different tactics than traditional social analytics, which used further insights about language AND categorized users according to times they tweet into morning people, afternoon people, evening people and night owls–providing further insights into mood.
And of course, this information is also very useful for understanding peak times to engage on Twitter (if you want to get on people’s good side).