Wednesday, October 12, 2011

Measuring Zeitgeist from the Tweet stream.

Golder and Macy have analyzed more than 509 million Twitter posts by 2.4 million users over a 2-year period in order to study collective mood (using Twitter to track the mood of nations sort of like using satellites to track the state of the atmosphere!). They used a freely available protocol provided by Twitter to download tweets originating from 84 countries between February 2008 and January 2010, and searched these messages for roughly 1000 words on a tried-and-tested list of words associated with positive (agree, fantastic, super) and negative (afraid, mad, panic) emotion. Despite very different cultures, geographies, and religions, the U.S., Canada, the UK, Australia, India, and English-speaking Africa all showed similar mood rhythms:
We identified individual-level diurnal and seasonal mood rhythms in cultures across the globe, using data from millions of public Twitter messages. We found that individuals awaken in a good mood that deteriorates as the day progresses—which is consistent with the effects of sleep and circadian rhythm—and that seasonal change in baseline positive affect varies with change in daylength. People are happier on weekends, but the morning peak in positive affect is delayed by 2 hours, which suggests that people awaken later on weekends.
A graphic from the article:
Hourly changes in individual affect broken down by day of the week (top, positive affect, PA; bottom,  negative affect, NA). Each series shows mean affect (black lines) and 95% confidence interval (colored regions). (Experimental psychologists have repeatedly demonstrated that positive and negative affect are independent dimensions. Positive affect (PA) includes enthusiasm, delight, activeness, and alertness, whereas negative affect (NA) includes distress, fear, anger, guilt, and disgust)

No comments:

Post a Comment