UW Data Science Seminar <http://data.uw.edu/seminar/>
Analysis, Visualization & Discovery
Wednesday October 8, 3:30pm — 389 Mary Gates Hall
Can Cascades be Predicted?*Jure Leskovec*
Assistant Professor of Computer Science, Stanford University
Social networks play a central role in spreading of information, ideas,
behaviors, and products. As such "contagions" diffuse from a person to
person they may go "viral," and large cascades can form. However, a growing
body of research has argued that virality and cascades may be inherently
unpredictable. Thus, one of the central questions is whether information
cascades can be predicted and possibly even engineered. In this talk, I
will discuss a framework for predicting cascades and making them go viral.
We study large sample of cascades on Facebook and find strong performance
in predicting whether a cascade will continue to grow in the future. The
models we develop help us understand how to create viral social media
content: by using the right title, for the right community, at the right
time.
BIO
Jure Leskovec <http://cs.stanford.edu/%7Ejure> is assistant professor of
Computer Science at Stanford University. His research focuses on mining
large social and information networks. Problems he investigates are
motivated by large scale data, the Web and on-line media. This research has
won several awards including a Microsoft Research Faculty Fellowship, the
Alfred P. Sloan Fellowship and numerous best paper awards. Leskovec
received his bachelor's degree in computer science from University of
Ljubljana, Slovenia, and his PhD in in machine learning from the Carnegie
Mellon University and postdoctoral training at Cornell University. You can
follow him on Twitter @jure <http://www.twitter.com/jure>.
