Abstract

Slides available (only for CL members)

With the advent of online tools, social networking has become a household world that is taken to allow for little more than communicating the latest you-tube video to friends. Similarly, Milgram’s original work on chains of relationships engendered the idea of “six degrees of separation”. Social network analysis is a powerful tool that can be used to infer information about a person, their preferences and their behaviours, sometimes with a higher precision than self-reported data.

The use of a network approach allows us not only to recommend preferences, but also verify profile data and predict affinity networks. In this talk I will review some of the work previously done on data-mining social networking data as well as some new research on cross linking networks from other data sets. These approaches are creating new computer science research areas, such as ’The Loading Problem’ where the required computation of an answer in disproportionate to cost of handling the information.

Short bio

I am a PostDoctoral follow (Oberassistent) in the Dynamic and Distributed Information Systems Group at the University of Zurich. I obtained my doctorate from the University of Waterloo in Canada and dabble in industrial and government research assignments.