If we want to model Twitter conversations with a network, we need to account for the context that users interact within. We propose a deep-learning approach to separating Twitter data out into contextualized networks. We then show that these contextualized networks have very different nodesets, topology, and central actors than observed in the non-contextualized networks. Our findings suggest that the dominant way of modeling social media conversations may be inaccurately portraying the nature of the conversations and the most important people in them.
Modularity Vitality has recently been identified as an efficient and powerful way of identifying community bridges and community hubs in unipartite networks. In this work, we expand this line of analysis to bipartite networks by deriving efficient …
We show that modularity vitality, or the difference between the modularity of a graph with and without a node, can be used to measure that node's contribution to community structure. We also derive a scalable way of computing this for all nodes. We then show that this measure identifies nodes which are more important to network integrity than existing measures can. This method fragmentes the PA Road network over 8 times more effectively than previous methods.
We analyze three textual data streams to characterize the change that occurred during the Ukrainian revolution of 2014. These data streams include legislative bill text, posts on Ukrainian political blogs, and Twitter data. Each stream provides a …
Modularity Vitality measures a node's contribution to group structure. In hashtag networks, then, Modularity Vitality can be used to select hashtag that contributes most to a topic found through community detection. We show that this leads to more interpretable topic analysis for a large Twitter dataset.
We identify time periods of disruption in the voting patterns of the Ukrainian parliament for the last three convocations. We compare two methods: ideal point estimation (PolSci) and faction detection (CS). Both methods identify the revolution in …
We develop a procedure for finding time-segments of community stability in dynamic networks. This also functions as a community-based event detector. Applying this to the legislative voting network in Ukraine's 8th convocation, we identify the Euromaidan Revolution as a major event, and show that the network structure is vastly different before and after.
In this study we compare two general methods of faction detection from Ukrainian Parliamentary roll call data, MacRae’s method and Gower’s method. Both methods were adapted to the special voting procedures and patterns of the Ukrainian Parliament, …
Current work in roll call modeling focuses on the legislative decision process and does not take advantage of the dynamic nature of legislation. Some political systems, such as Ukraine’s Verkovna Rada, are inherently dynamic, and should be modeled as …