New Map Measures Mood Of ‘Twitter Nation’
Researchers from Northeastern University and Harvard Medical School have constructed a “˜Twitter Mood Map’ that measures the mood of America.
The scientists used millions of “˜tweets’ from the online social networking site to create the map, which revealed that Americans are cheeriest in the morning and in the evening, with happiness peaking on Sunday morning and bottoming out on Thursday night.
In general, West coast tweeters were considerably happier than their East coast counterparts, the study found. And residents of California, Miami and the southern states were among the most content, the researchers said.
A chart entitled “Pulse of the Nation: U.S. Mood Throughout the Day, as inferred from Twitter”, available at http://www.ccs.neu.edu/home/amislove/twittermood/, reveals the cheerful moods moving from East to West and back again throughout the day.
The researchers acknowledge their findings are not a truly scientific representation of the public mood, since Twitter users tend to be more tech-savvy and live in large cities, and therefore represent just a small portion of the general population. However, the map still has potential as a tool for providing real-time analysis of vital issues.
"Even though individual tweets are pointless to anyone besides your followers, in aggregate there is a lot of meaningful information that can be an instrument to see how people feel about things, whether it’s public reaction to a politician’s speech or a consumer attitudes about a brand," said Sume Lehmann, a postdoctoral researcher who worked on the study, during an interview with Reuters.
Lehmann and the other researchers used a psychological word-rating system developed by the National Institute of Mental Health’s Center for the Study of Emotion and Attention to evaluate keywords in roughly 300 million tweets based on how they make people feel.
For instance, tweets containing words such as “love” received high mood rankings, whereas those with words such as “death” scored low marks.
The researchers used the results to construct maps based on the location of the messages and the general moods they represent.
Having such real-time data could ultimately help monitor how the collective mood of the Twitter Nation changes in response to certain events, such as a sudden spike or dip in the stock market, or the result of a major sporting event, the researchers said.
"Our method is a new way to extract information about people everywhere,” Lehmann said.
“Using this strategy, we could track how ideas and Internet memes spread.”
The map could also be useful in rapidly mobilizing users for certain events, such as a drive for emergency relief donations.
"It’s absolutely crucial to have real-time indicators about how the public feels, not in months, but in a matter of hours and days,” Reuters quoted Johan Bollen, a computer scientist who was not involved in the study, as saying.
"The potential there is tremendous, on both an individual and societal level.”
—
On the Net: