Researchers from the Northeastern University and Harvard University have released the findings of a study about the mood on Twitter over time. So, how does the mood of the United States change during one day?
The emotional measurements were plotted using a combination of cartograms and heat maps that quickly give access to the most important measurements: The amount of Tweets is displayed as the geographical scale and the mood is represented by the color of the county.
A number of interesting trends can be observed in the data. First, overall daily variations can be seen, with the early morning and late evening having the highest level of happy tweets. Second, geographic variations can be observed (second graph), with the west coast showing happier tweets in a pattern that is consistently three hours behind the east coast.
Weekly trends can be observed as well, with weekends happier than weekdays. The peak in the overall tweet mood score is observed on Sunday mornings, and the trough occurs on Thursday evenings.
The dataset consists of over 300 million tweets collected over the time period from Sep 2006 – Aug 2009. The mood of each tweet was inferred using the ANEW wordlist by NIMH Center for Emotion and Attention (CSEA) at the University of Florida.
Twitter continues to be an interesting source of data and the plots at hand achieve to reveal underlying patterns. We need to keep in mind that Twitter’s user base is not representative for all U.S. citizens but with over 190 million users worldwide it seems to give a good indication about what’s going on.