We often hear that the Internet is unpredictable, that it’s the “Wild West.” That would seem to be especially true of a social medium such as Twitter. After all, tweets are by definition instant and short-lived. But in a paper I and my co-authors just submitted to the Annals of Applied Statistics, we describe a model we have developed that predicts how popular a tweet is likely to be within just a few minutes of when the “root tweet” is posted.
And anyone who wants to can now try out our model by visiting www.twouija.com.
Log on to Facebook or Twitter any time of day, and you’ll find a familiar scene: people asking questions. “In a book rut – can anyone recommend a good novel?” “Boyfriend and I had a fight – should I dump him?” or “Am shopping for a newsuit — which color would look best on me?”
Social media has made it easier than ever before to ask questions of our friends, acquaintances, and other contacts. In some ways this is a good thing because we have more information to weigh, analyze, and consider before we make a decision. But in other ways, all this information and all these opinions can result in cognitive overload. It’s like going into the cereal aisle at the grocery store for every single decision.