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 datasets, simply counting the words and averaging their happiness content produces “reliable” results.
I lead biz dev & sales at UNION METRICS. We do impact and engagement analytics for Twitter (TweetReach) and Tumblr.
Born and raised in Atlanta, I completed my Master's in Digital Media at Georgia Tech and moved to San Francisco in April 2010 to consult on new media strategy for top companies and consumer brands.