Full Interview: Jure Leskovec on predictive social network analysis

jure-2b.jpg                                                                                      Jure Leskovec

Almost everything you do online is tracked, measured, and filed away in a database somewhere. As David Fewer told Nora earlier this week, as we move around digital networks, we leave behind digital traces like footprints in the snow.

On previous episodes of Spark, Nora has talked to researchers who analyse those footprints in search of useful patterns. For example, Nora interviewed Albert-Laszlo Barabasi in 2010 about the predictably of human behaviour. And on Spark 124, Nora talked to Valdis Krebs, whose work focuses on patterns of communication rather than the content of communication.

Last week, Nora interviewed Jure Leskovec, a computer science prof at Stanford who recently won a Microsoft Research Faculty Fellowships for his work on social network analysis. Using networking mining and modeling techniques, Jure and his colleagues at Stanford's computer science department analyse past human behaviour online to predict future outcomes. For instance, they can predict who your next friends on Facebook will be.

A shorter version of Nora's interview with Jure will air on an upcoming episode of Spark, but you can hear the full, uncut interview below, or download the MP3. [runs 27:47]

Download Flash Player to view this content.

If you like hearing these extended interviews, why not subscribe to Spark Plus? You'll get regular weekly episodes, plus additional blog-only content like this. [Subscribe via RSS] or [Subscribe with iTunes]


Comments are closed.