People share huge amounts of personal information in social media, but they reveal more beyond what they explicitly post. Algorithms can leverage information from their social network, language use, profile information, and other digital traces to uncover personal secrets and predict future behaviors. I will discuss how we generate these predictions, particularly focused on the linguistic analysis that supports many results (mine and others'), as well as some related ongoing work on detecting trolling behavior.
Jennifer Golbeck is Director of the Social Intelligence Lab and an Associate Professor in the College of Information Studies at the University of Maryland, College Park. Her research focuses on analyzing and computing with social media, focused on predicting user attributes, and using the results to design and build systems that improve the way people interact with information online.