Abstract
Information diffusion is the spread of information within a network. In this thesis, we model information diffusion as a survival process. We have adopted an existing algorithm called NetRate for modelling information diffusion. This model involves finding the distribution of trasmission time between two nodes in the network. We modify NetRate’s concave-down log-likelihood expression by adding partial parentage information and formulate an Expectation-Minimization (EM) algorithm to learn the parameters. We also describe a simulation scheme for NetRate inspired by point process simulation strategies. Using the assumptions of the NetRate model, we derive a a method to model popularity as a function of time. In order to showcase the insights offered by NetRate, we explore a real-world example involving two kinds of software vulnerabilities: Exploited and non-exploited vulnerabilities. Finally, We derive a scheme for transforming infection times so that a goodness of fit test can be performed using Kolmogorov- Smirnov (KS) test statistic.
