Date of Award
8-2026
Degree Name
Doctor of Philosophy
Department
Statistics
First Advisor
Kevin H. Lee, Ph.D.
Second Advisor
Joshua Naranjo, Ph.D.
Third Advisor
Hyun Bin Kang, Ph.D.
Fourth Advisor
Sangwoo Lee, Ph.D.
Keywords
Bipartite networks, bipartite sbm, community detection, node-level covariates, stochastic block models
Abstract
In this age, monumental webs of data demands for perpetual cultivation of ways to untangle these webs of information. One of the many curiosities is how to systematically group entities. When clustering, one avenue to take is ascertaining the interconnectedness between the data points, and gauging their influence to each other. This perspective is programmed to model the relationships between the data presented as a network. Many of the methods being used today are algorithm-based, which may pose limitations in understanding and explaining the uncertainty revolving around the data. Hence, it is proposed to steer towards a model-based approach that learns the underlying behavior of data. One of which is the Stochastic Block Models (or SBMs).
SBMs have been one of the most frequented models for network data due to their interpretability and flexibility. Despite being the core of multiple researches, there are limited studies on incorporating node-level attributes into SBMs with complex network composition such as bipartite networks. Thus, this research is focused on formulating a clustering technique using SBMs that will leverage the node covariates within a bipartite network.
The simulation study reveals that integrating the characteristics of nodes into the bipartite SBMs enriches the clustering performance of the models—the block memberships formed by the attributed models are much closer to the ground truth as compared to the pure bipartite SBMs. This behavior provides confidence in utilizing the proposed model on a synthetic Netflix data and establishing a recommendation system to the Netflix users based on the node-level features of the Watchers and Content groups.
Access Setting
Dissertation-Open Access
Recommended Citation
Percival, Geraldine Elaine, "Community Detection in Bipartite Networks using Bipartite Stochastic Block Models with Node-Level Covariates" (2026). Dissertations. 4295.
https://scholarworks.wmich.edu/dissertations/4295