Are You Tweeting From the Happiest State?

By Rachel Ramsey February 20, 2013

If you’re tweeting from Hawaii, then the answer is yes. A team at the Vermont Complex Systems Center recently posted its new analysis of 10 million geotagged tweets to arXiv.org, calling its creation a heonometer, to determine the happiest and saddest states in the U.S.

“The Geography of Happiness: Connecting Twitter sentiment and expression, demographics, and objective characteristics of place,” studied the correlations between real-time expressions of individuals across the U.S. and a wide range of emotional, geographic, demographic and health characteristics.

The report analyzed more than 80 million words generated over the course of several recent years on Twitter. Not only does it tell us what the top happy and sad states are, but the results show how social media may potentially be used to estimate real-time levels and changes in population-level measures such as obesity rates.





 Image
via “The Geography of Happiness” report

Making the list as the happiest states are Maine, Nevada, Utah and Vermont. Louisiana, Missisippi, Maryland, Michigan and Delaware are the top saddest states.

The study also looked at the results for 373 urban areas to rank the happiest and least-happy cities. Vacation destination Napa, Calif., was determined to be one of the happiest cities along with Longmont, Colo.; San Clemente, Calif.; Santa Fe, N.M.; and Santa Cruz, Calif.

The five most bummed-out cities according to average word choices were Beaumont, Tex.; Albany, Ga.; Texas City, Tex.; Shreveport, La.; and Monroe, La. Again, researchers found liberal use of swear words to be a key factor in a city's overall happiness score.

The researchers 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 researchers admit their technique ignores context, they say that for large data sets, simply counting the words and averaging their happiness content produces "reliable" results.

According to The Atlantic, the researchers failed to look at Twitter in Spanish, which could have made different cities appear happier on this list. Click here to read the entire report.

In a related study, researchers also turned to Twitter to find out when we are happiest. Using values assigned to words contained in 4.6 billion tweets, researchers tracked how levels of happiness rose and subsided. The last months of each year, Saturdays and the early mornings are happy times, while January, the first days of the week and late-nights are not. This survey used the same service as the state study, Mechanical Turk.




Edited by Jamie Epstein

TechZone360 Web Editor

SHARE THIS ARTICLE
Related Articles

Google says Encryption Keys are in the Ignition

By: Peter Bernstein    7/31/2015

It has been such a wild few days in the cyber security area with all of the hacks, data breaches, exposures by security folks that all Android and wea…

Read More

Chattanooga Fiber Network Triple Play: Smart Grid, Gigabit, Green Energy

By: Doug Mohney    7/31/2015

Chattanooga is unique for a gigabit class network that covers the entire community, serving over 150,000 homes and businesses. Its advantages go far b…

Read More

Strategy Analytics: Shakeups Abound in the Tablet Market

By: Steve Anderson    7/31/2015

While the tablet market is something of a lesser phenomenon compared to the smartphone market, there's still quite a bit happening. A new report from …

Read More

Chattanooga: Much More than GigCity

By: Doug Mohney    7/31/2015

It is far too simple to say Chattanooga's high-speed fiber optic network is the cornerstone to the city's future growth. While city leaders and operat…

Read More

Taking a Look into Windows 10

By: Joe Rizzo    7/31/2015

On July 29, 2015 the long awaited release of Windows 10 arrived. You may have noticed that Microsoft went from version 8.1 to Windows 10, which is due…

Read More