WWW-15 Tutorial
Large Scale Network Analytics with SNAP

Tutorial information

Techniques for social media modeling, analysis and optimization are based on studies of large scale networks, where a network can contain hundreds of millions of nodes and billions of edges. Network analysis tools must provide not only extensive functionality, but also high performance in processing these large networks.

The tutorial will present Stanford Network Analysis Platform (SNAP), a general purpose, high performance system for analysis and manipulation of large networks. SNAP is being used widely in studies of web and social media. It consists of open source software, which provides a rich set of functions for performing network analytics, and a popular repository of publicly available real world network datasets. SNAP software APIs are available in Python and C++.

The tutorial will cover all aspects of SNAP, including SNAP APIs and SNAP datasets. The tutorial is targeted toward entry level audience with some programming background, thus the Python API will be discussed in more detail than the C++ API. The tutorial will include a hands-on component, where the participants will have the opportunity to use SNAP on their computers.

The tutorial will be held at 24th International World Wide Web Conference in Florence, Italy, May 18 to 22, 2015.

Tutorial outline

Tutorial materials

Who should attend

Participants are expected to have entry level programming experience, preferably with Python or C++ for maximum benefit. Background in basic graph and network concepts and algorithms is helpful although it is not required.

The goal for the tutorial is for the participants to learn about the resources provided by SNAP and how to apply them to network analytic tasks in web and social media. The participants will install SNAP on their computers and gain hands-on experience with SNAP through a set of exercises.


Jure Leskovec is an assistant professor of Computer Science at Stanford University. His research focuses on the analysis and modeling of large real-world social and information networks as the study of phenomena across the social, technological, and natural worlds. Problems he investigates are motivated by large scale data, the Web and Social Media. Jure received his PhD in Machine Learning from Carnegie Mellon University in 2008 and spent a year at Cornell University. His work received five best paper awards, won the ACM KDD cup and topped the Battle of the Sensor Networks competition.

Rok Sosic is a senior researcher in Prof. Leskovec's group at Stanford University, working on tools for large scale network analytics. He published over 40 papers, including a best paper at the Supercomputing conference and a top 10 paper in the high-performance distributed computing field. He lead one of the first grid computing deployments on Wall Street and later headed engineering at Turbolinux, a world's top 3 Linux distribution at that time with 10's of millions of users. Most recently, he lead engineering efforts at SkyGrid, a personalized online news aggregation platform with millions of downloads, also named by Apple the App Store Best News App in 2011. Rok received his PhD in Computer Science from University of Utah.