@article{Pfeiffer_Neville_2021, title={Methods to Determine Node Centrality and Clustering in Graphs with Uncertain Structure}, volume={5}, url={https://ojs.aaai.org/index.php/ICWSM/article/view/14187}, DOI={10.1609/icwsm.v5i1.14187}, abstractNote={ <p> <!-- p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 9.0px Times; color: #1a1a18} --> <p class="p1">Much of the past work in network analysis has focused on analyzing discrete graphs, where binary edges represent the &ldquo;presence&rdquo; or &ldquo;absence&rdquo; of a relationship. Since traditional network measures (e.g., betweenness centrality) assume a discrete link structure, data about complex systems must be transformed to this representation before calculating network properties. In many domains where there may be <em>uncertainty </em>about the relationship structure, this transformation to a discrete representation will result in a lose of information. In order to represent and reason with network uncertainty, we move beyond the discrete graph framework and develop social network measures based on a <em>probabilistic </em>graph representation. More specifically, we develop measures of path length, betweenness centrality, and clustering coefficient&mdash; one set based on sampling and one based on probabilistic paths. We evaluate our methods on two real-world networks, Enron and Facebook, showing that our proposed methods more accurately capture salient effects without being susceptible to local noise.</p> </p> }, number={1}, journal={Proceedings of the International AAAI Conference on Web and Social Media}, author={Pfeiffer, Joseph and Neville, Jennifer}, year={2021}, month={Aug.}, pages={590-593} }