Twitter Shows It’s True Colours
Pulse of the Nation: U.S. Mood Throughout the Day inferred from Twitter.
A study recently at Northeastern University in Boston created a mood map according to different tweets in the United States. The researchers there analyzed the 140-character long messages, deciphering mood and ranging it between least happy to most happy. There is a psychological word-rating system that is used to look at the 300+ million tweets and determine if they are happy or sad.
They found that people were most happy first thing in the morning (odd – I guess Tweethards are also morning people) and later in the evening. On a weekly trend, Sundays are the happiest, followed closely by Saturdays (no surprise there) and Thursday evenings found people the least happy.
“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 politicians speech or a consumers attitudes about a brand.” said Sue Lehmann, one of the researchers.
This makes me wonder how much the government can use this information to judge it’s populous and determine where they have to campaign more. Say after a great Obama speech, the western coast is tweeting all red, then the government can learn to campaign better in that area and have to tailor it’s message better to those people. For me personally, I’d like to see the MoodMap for specific days, like when Lebron James announced he was going to play in Miami. (Maybe this explains Ohio’s grumpyness – See below).
There’s a time lapse video included here, and just so you’re not confused; The map is skewed because of the large population mass found in each region. You will see California bulge and shrink as more users in that area Tweet. See more in the picture below.
A cartogram is a map in which the mapping variable (in this case, the number of tweets) is substituted for the true land area. Thus, the geometry of the actual map is altered so that the shape of each region is maintained as much as possible, but the area is scaled in order to be proportional to the number of tweets that originate in that region. The result is a density-equalizing map. The cartograms in this work were generated using the cart software by Mark E. J. Newman, available at http://www-personal.umich.edu/~mejn/cart.
I found it particularly interesting that during the time lapse, you can see that the states of New Mexico (on the top left corner of Texas) and Ohio (in the middle of the map, with the little hook on the right side) seem to stay red for the entire course of the day. Now, I don’t know if this has to do with the lack of tweets coming from that area, thus making the small sample size skew the results, or if people in those two states are really just grumpy all day long. Note to self: Do not go to Ohio/New Mexico on Vacation.
