Study

A new study from Carnegie Mellon University shows that analyzing data from Twitter yields the same results as conducting a public opinion poll. We’re willing to bet it probably costs less, takes less time and annoys fewer people, as well. A CMU team from the computer science department looked at sentiments expressed in a billion Twitter messages between 2008 and 2009. The researchers then use simple text analysis methods to filter out updates about the economy and politics and determine if the overall sentiment of the update was positive or negative. The CMU team found that people’s attitudes on consumer confidence and presidential job approval were similar to the results generated by well-reputed, telephone-conducted public opinion polls, such as those conducted by Reuters, Gallup and pollster.com. ...

Facebook has extended its “Gross National Happiness” prototype app to 18 new countries. The app analyzes words in status updates like “awesome” or “tragic” to track changes in the collective emotional state of its users. When Facebook applied the methods to its U.S. userbase last year, it found that happiness went way up on holidays and way down when celebrities like Michael Jackson or Heath Ledger passed away. While the results of the study weren’t surprising, the idea of using status updates to measure national happiness was a novel one. ...