Twitter chatter reflects global moods: study

Study of two million Twitter users' tweets finds the obvious, but suggests potential for more accurately predicting shifts in attitudes and perceptions.
Written by Joe McKendrick, Contributing Writer

In previous posts, we discussed how Twitter tweet analyses have determined that future events or stock market moves could be sensed before they happen.

Now, a new study of close to 800 million tweets from across the globe says the tone of this chatter aligns with general daily mood swings. People tend to brighten up by breakfast time, go into a slump in the afternoon, then brighten up in the evening.  In addition, collective moods were most sour at the beginning of the week, and brightened up on weekends.

Obvious stuff, of course, but this is the first time such moods have been digitally and collectively measured from a global sample.

As reported in The New York Times:

"Drawing on messages posted by more than two million people in 84 countries, researchers discovered that the emotional tone of people’s messages followed a similar pattern not only through the day but also through the week and the changing seasons. The new analysis suggests that our moods are driven in part by a shared underlying biological rhythm that transcends culture and environment. The report, by sociologists at Cornell University and appearing in the journal Science, is the first cross-cultural study of daily mood rhythms in the average person using such text analysis."

The study covered 2.4 million Twitter users between February 2008 and January 2010. The researchers employed a program that associated words such as “awesome” and “agree” with positive emoticons, as well as negative terms and emoticons.

One interesting surprise: moods did not darken during the winter months, as would be generally assumed.

Such studies open up the collective mind of social media users, and may be instrumental in helping to predict shifts in sentiment or preferences -- for everything from products to government policies.

This post was originally published on Smartplanet.com

Editorial standards