(YouTube Link)
This time-lapse video shows the changing moods of people in America over the course of a day, as ascertained by emotional keywords that they use on Twitter. It was created by computer scientist Alan Mislove at Northeastern University in Boston:
Mislove speculates that a signal shines though because the sheer abundance of data means that occasional misinterpretations are lost in the crowd. Bryan Routledge at Carnegie Mellon University in Pittsburgh, Pennsylvania, agrees. With colleagues, he recently used a similarly simple analysis of words in tweets to determine whether Twitter mirrors conventional opinion polls. "The volume is massive, so the subtle stuff kind of washes out," he says.
Because Twitter data is publicly available, Routledge says mood can be sampled more quickly, simply and cheaply than using traditional polling tools – albeit more crudely.
Steven Gray at University College London, who also crowdsources data through Twitter, agrees. For all of the problems with decoding the data, "Twitter offers researchers a unique, live data set that changes by the minute", he says.
Link via Geekosystem | Project Website | Previously: Tweet Sleeve: Wear Your Emotions on Your Sleeve
"This time-lapse video shows the changing moods of people in America over the course of a day, as ascertained by emotional keywords that they use on Twitter."
It's not faulty because it uses Twitter. It uses Twitter because that's what it is. Something can't be at fault for using Twitter, when "using Twitter" is in it's definition. It never claimed to be an ultimate, super accurate, indication of how everyone in the States is actually feeling.
Also, go NU.
I found twtrstat (http://www.twtrstat.com/Mood.aspx) provides twitter sentiment map that can be interesting.