Ruling Out Static Latent Homophily in Citation Networks

TL;DR

This paper applies algebraic geometric methods and semidefinite programming to citation and coauthor networks to determine whether observed patterns are due to shared interests or other factors, advancing causal analysis in scientific collaboration.

Contribution

It introduces algebraic geometry and SDP relaxations to citation network analysis, providing a novel approach to rule out static latent homophily as a cause of observed patterns.

Findings

Latent homophily can be statistically ruled out as the sole cause of network patterns.

Algebraic geometry offers a new analytical tool for studying content-related social influences.

The method bridges concepts from quantum physics and social network analysis.

Abstract

Citation and coauthor networks offer an insight into the dynamics of scientific progress. We can also view them as representations of a causal structure, a logical process captured in a graph. From a causal perspective, we can ask questions such as whether authors form groups primarily due to their prior shared interest, or if their favourite topics are 'contagious' and spread through co-authorship. Such networks have been widely studied by the artificial intelligence community, and recently a connection has been made to nonlocal correlations produced by entangled particles in quantum physics -- the impact of latent hidden variables can be analyzed by the same algebraic geometric methodology that relies on a sequence of semidefinite programming (SDP) relaxations. Following this trail, we treat our sample coauthor network as a causal graph and, using SDP relaxations, rule out latent homophily as a manifestation of prior shared interest leading to the observed patternedness. By introducing algebraic geometry to citation studies, we add a new tool to existing methods for the analysis of content-related social influences.