Can Happiness Be Found in 10 Million Tweets?

Media |

Courtesy: Mrs Logic

After pouring over more than 10 million geo-tagged tweets, researchers from the Vermont Complex Systems Center at the University of Vermont have concluded Hawaiians are the happiest people in America. Louisianans, not so much.

According to The Atlantic, researchers combed Twitter accounts state-by-state for “happy” and “sad” words in order to determine a location’s overall mood. They coded each tweet for its happiness content “based on the appearance and frequency of words determined by Mechanical Turk workers to be happy (rainbow, love, beauty, hope, wonderful, wine) or sad (damn, boo, ugly, smoke, hate, lied).”

While The Atlantic points out that the study has inherent flaws (technique ignores context, only captures tweets in English), it seems researchers’ “happiness data” closely matches each state’s income and obesity rate.

“The research shows that social networks have a lot of promise for these types of surveys, and also that there are still some major limitations,” CNN reported. “Researchers point out that only 15% of online adults are using Twitter, and those users don’t accurately represent the demographics of the United States.”

While tweeting may be an expression of the “Right Now” with respect to individual happiness, it seems that tweeters in certain areas may be more alike than they think. It’s interesting to think that 140 characters can be used to measure a place’s overall well-being…  or, at least, how often people tweet about #rainbows.



Keep in touch

Subscribe to thoughts on strategy and design, plus whatever we’re up to lately.