Analyzing Twitter’s mood swings

There have been loads of studies data mining social networking sites, chat rooms, and all manner of material on the blogosphere. But this is new: researchers from Cornell University are focusing on daily data crossing cultural and geographical boundaries to show that people’s daily mood patterns are closely correlated to biological patterns.

“There’s just a torrent of new digital data coming into the field, and it’s transforming the social sciences, creating new lenses to look at all sorts of behaviors . . . [its] very exciting, because it complements previous findings and expands on what is known about how mood fluctuates,” said Peter Sheridan Dodds, a researcher at the University of Vermont.

This new research gathered data on two million people (!) in 84 countries (!) and discovered that people’s emotional tone in their Twitter messaging moved according to time of day. Positive mornings, followed by low afternoons, uplifting again in the evening. Researchers also looked at seasonal patterns and found that mood is influenced by night day, winter and summer.

There was no surprise that people’s moods went down as the work week began and stayed low throughout the work day. However, the mid day lows did not change on the weekend. That pattern continued regardless of day of the week. That may be an indication that the dip in mood is not due to work, but is cyclical or circadian in nature.

A word of caution from Dan Gilbert, a Harvard psychologist, “Tweets may tell us more about what the tweeter thinks the follower wants to hear than about what the tweeter is actually feeling. In short, tweets are not a simple reflection of a person’s current affective state and should not be taken at face value.”

Source: Science, MedicalNewsToday