Five hundred million tweets are broadcast worldwide every day on Twitter. With so many details about personal lives, the social media site is a data trove for scientists looking to find patterns in human behaviors, tease out risk factors for health conditions and track the spread of infectious diseases. By analyzing emotional cues found in the tweets of pregnant women, for instance, Microsoft researchers developed an algorithm that predicts those at risk for postpartum depression. And the U.S. Geological Survey uses Twitter to track the location of earthquakes as people tweet about tremors.
Until now, most interested scientists have been working with a limited number of tweets. Although a majority of tweets are public, if scientists want to freely search the lot, they do it through Twitter's application programming interface, which currently scours only 1 percent of the archive. But that is about to change: in February the company announced that it will make all its tweets, dating back to 2006, freely available to researchers. Now that everything is up for grabs, the use of Twitter as a research tool is likely to skyrocket. With more data points to mine, scientists can ask more complex and specific questions.
Link to the full article
Originally published in the Scientific American
No comments:
Post a Comment