Want to monitor an earthquake, track political activity or predict the ups and downs of the stock market?
esearchers have found a bonanza of real-time data in the torrential flow of Twitter feeds.
They discovered that in the crisis, Twitter crowds reflexively sorted facts from falsehoods, exercising a collective wisdom on the fly. She found enough measurable differences in language, citations and posting patterns to devise a way to assess the credibility of Twitter texts automatically, with an accuracy of about 70%.
Researchers concede that their studies have some limitations. Twitter users tend to be younger adults, urban, more affluent and less likely to have children; they are not a cross-section of society as a whole. Still, researchers say, there is considerable diversity—demographic, national and cultural—among those who use the service, and it is possible to make meaningful generalizations from the flow of their messages.
At Cornell University, network analysts discovered that bad news appeared to fade fastest, weighed down by words with negative connotations. Good news more often floated to the top, buoyed in part by words with positive associations.