Critique of Graph Cluster Randomization: Network Exposure to Multiple Universes

Abstract

In this paper I will be reviewing and evaluating the work of Johan Ugander and Jon Kleinberg (both from Cornell University) and Brian Karrer and Lars Backstrom (both from Facebook), entitled Graph Cluster Randomization: Network Exposure to Multiple Universes, presented at the 2013 International Conference of Knowledge DIscovery and Data Mining. After a brief summary of the paper and its findings, I present the author's background and related previous work - to find that graph cluster randomization proves to be a truly useful method for social networks and has a wide array of future applicability. Subsequenlty I conduct a brief overview of related work and possible improvements, followed by my personal reflections and suggested future work pathways. I finish with a brief conclusion.

Keywords: social network, randomization, A/B testing, network exposure

Summary

In this paper I will be reviewing and evaluating the work of Johan Ugander and Jon Kleinberg (both from Cornell University) and Brian Karrer and Lars Backstrom (both from Facebook), entitled Graph Cluster Randomization: Network Exposure to Multiple Universes (GCR), presented at the 2013 International Conference of Knowledge DIscovery and Data Mining and featured on Facebook's research page (Ugander 2013).