Community detection in bipartite signed networks is highly dependent on parameter choice

2024-05-13

arXiv.org

AI Summary

This paper addresses the reliability of community detection in signed bipartite networks (e.g., legislative voting, product reviews), revealing that existing methods frequently yield spurious structures in the absence of ground-truth communities and exhibit high sensitivity to parameter choices. It presents the first systematic robustness evaluation of community detection in such networks, identifying parameter sensitivity as a fundamental challenge. Through empirical analysis—including projection-based algorithms, synthetic benchmark generation, and real-world datasets (U.S. Congressional voting records and Amazon product reviews)—combined with comprehensive parameter sweeps and external validation, the study demonstrates widespread false positives and severe performance instability across mainstream methods. The core contribution is the formal establishment of “parameter robustness assessment” as a necessary prerequisite for community detection, alongside a reproducible, principled framework for reliability analysis specifically tailored to signed bipartite networks.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Safety and Robustness
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Decision-making processes often involve voting. Human interactions with exogenous entities such as legislations or products can be effectively modeled as two-mode (bipartite) signed networks-where people can either vote positively, negatively, or abstain from voting on the entities. Detecting communities in such networks could help us understand underlying properties: for example ideological camps or consumer preferences. While community detection is an established practice separately for bipartite and signed networks, it remains largely unexplored in the case of bipartite signed networks. In this paper, we systematically evaluate the efficacy of community detection methods on projected bipartite signed networks using a synthetic benchmark and real-world datasets. Our findings reveal that when no communities are present in the data, these methods often recover spurious user communities. When communities are present, the algorithms exhibit promising performance, although their performance is highly susceptible to parameter choice. This indicates that researchers using community detection methods in the context of bipartite signed networks should not take the communities found at face value: it is essential to assess the robustness of parameter choices or perform domain-specific external validation.

Problem

• Group Detection
• Network Analysis
• Parameter Sensitivity

Innovation

• Bipartite Sentiment Networks
• Parameter Sensitivity Analysis
• False Positive Minimization