Sociologists analyzed tweets, coming up with some not so surprising insights about weekday moods of users
On Thursday, the New York Times reported that sociologists at Cornell University have issued a scientific report on how our moods are reflected in our daily tweets.
“Drawing on messages posted by more than two million people in 84 countries,” the Times noted, “the researchers determined that for the average user in each country, positive posts crested around breakfast time, from 6 a.m. to 9 a.m.; they fell off gradually until hitting a trough between 3 p.m. and 4 p.m., then drifted upward, rising more sharply after dinner.”
This is not exactly, “Well, duh…” stuff for this particular “user.” Given that the report was “the first cross-cultural study of daily mood rhythms within the average person, using such text analysis,” and upon some reflection finding myself to be an average person, I thought about the proffered data — though admittedly from the viewpoint of an indifferent, not to say slothful, tweeter.
That’s right, tweeting is work. In order to tweet something out in that 6-7 a.m. time frame, I first have to wrest my iPhone from the grasp of my nine-year-old, who is playing “Angry Birds” on it, and then, having forgotten my glasses on the nightstand, would only be capable of thumb-typing, even in all caps, “FWRSH SIDE NIR BLEEp7” or some such.
I will frankly have no idea of my mood until I crank up and deploy the espresso machine. At this stage some tweets might be issued, such as, to my wife, already in the kitchen on her iPhone: “Will you and your $19 a pound ‘Intelligentsia’ coffee beans clear out? Coming in. Pls remove dunkin d beans from freezer.”
Shortly thereafter could come a, “Much better now,” but who really cares?
No one, except, perhaps, sociologists Scott A. Golder and Michael W. Macy, the study’s authors. They performed text analysis on each message“using a standard computer program that associates certain words, like ‘awesome’ and ‘agree,’ with positive moods, and others, like ‘annoy’ and ‘afraid,’ with negative states." They included so-called emoticons, the face symbols like “:)” that punctuate digital missives.
Okay, I get it. So at 8:17 a.m., something like this might emerge: “Due at work within the hr. F—king awesome! Maybe my editors will agree day off is needed.”
Or conversely, “Time to go annoy my colleagues with my kid’s slingshot and bb’s, which for some reason they are all afraid of. (^ _^) ”
See, this is where well-meaning studies go wrong.
As the authors and the Times have indeed perceived, “on Twitter, people routinely savage others with pure relish and gush sarcastically — and the software is not yet sophisticated enough to pick up these subtleties.”
E.g., a simple, “You dirtbag—that was the most disgusting bachelor party I’ve ever been to” might be misconstrued as negative.
A University of Vermont researcher who’s been doing text analysis of Twitter messages worldwide looking for cussing has found that “Swearing goes up with negative mood in the very same way….it tracks beautifully with the pattern they’re showing.”
The researchers discovered that—although people’s overall mood was lowest on Monday afternoons and through Tuesday (Well duh! Now I’ll say it) and improved to its peak on Saturday and Sunday (double duh!), the happiness pattern on weekend days followed the same shape, albeit hours later.
To which I’d simply say, “#mmmffrzzz”.