Fig 1 - uploaded by Rebecca Willett
Content may be subject to copyright.
Graphical representation of the proposed Bayesian model. The plates indicate repetition, and the filled circle around Bt means that its value is observed. The dashed circles indicate random variables that are gamma distributed, with the corresponding hyperparameters omitted from the plot for simplicity.
Source publication
A statistical framework for modeling and prediction of binary matrices is presented. The method is applied to social network analysis, specifically the database of US Supreme Court rulings. It is shown that the ruling behavior of Supreme Court judges can be accurately modeled by using a small number of latent features whose values evolve with time....
Context in source publication
Citations
... There are models that allow change in the topic structure of a corpus of text data [4]. Similarly, statistical models for dynamic networks has grown much more sophisticated [5,6,7]. Evolving exponential random graph models [8] and stochastic actor based models [9] provide powerful tools for investigating dynamic network structure. ...
The last decade has seen great progress in both dynamic network modeling and topic modeling. This paper draws upon both areas to create a Bayesian method that allows topic discovery to inform the latent network model and the network structure to facilitate topic identification. We apply this method to the 467 top political blogs of 2012. Our results find complex community structure within this set of blogs, where community membership depends strongly upon the set of topics in which the blogger is interested.
This paper outlines techniques for optimization of filter coefficients in a spectral framework for anomalous subgraph detection. Restricting the scope to the detection of a known signal in i.i.d. noise, the optimal coefficients for maximizing the signal's power are shown to be found via a rank-1 tensor approximation of the subgraph's dynamic topology. While this technique optimizes our power metric, a filter based on average degree is shown in simulation to work nearly as well in terms of power maximization and detection performance, and better separates the signal from the noise in the eigenspace.