Summary:
Recent research has focused on the monitoring of planetary-scale online data for improved detection of flu outbreaks, global mood patterns, movements in the stock market, political revolutions, and many other important phenomena. However, none of these methods take advantage of the network structure in these data sources to identify key nodes, and increasingly the amount of data available online exceeds our capacity to monitor it in real time. In this talk I'll introduce an on-working analytic model of the contagious spread of information in a large-scale publicly-articulated social network and show that a simple method can yield not just early detection, but advance warning of contagious outbreaks. In this method, we randomly choose a small fraction of nodes in the network and then we randomly choose a “friend” of each node to include in a group for monitoring. Using six months of data from Twitter, we show that this friend group is more central in the network and it helps us to detect viral outbreaks of the use of novel hashtags about 6 days earlier than we could with an equal-sized randomly chosen group.
Short bio:
Manuel García-Herranz is a postdoctoral associate at the Ambient Intelligence Laboratory of the Universidad Autónoma de Madrid, where he received his Ph.D. in Computer Science in 2009. He is interested in data-driven modeling of human behavior, and in how this is influenced by the technological interfaces in its environment. In the past, he worked on HCI for large data analysis (Carnegie-Mellon University, 2010) and information epidemiology in computational social networks (UCSD, 2011).
