Reconstructing signed relations from interaction data

This study presents a statistical network method to infer weighted signed relations from interaction data. The method, called the Φ-method, assumes that a statistical over-representation of interactions signals a positive relation and an under-representation signals a negative relation. TheΦ-method was tested on four classical interaction datasets and showed promising results in predicting reported relations and reconstructing the underlying relational networks of the communities.

The Φ-method relies on the main assumption that a statistical over-representation of interactions signals a positive relation and an under-representation signals a negative relation.
Why This Matters for Scientists

You may want to use the Φ-method to infer weighted signed relations from interaction data, especially when dealing with communities where data about signed relations is rare. The method has been shown to be effective in predicting reported relations and reconstructing relational networks.

Quick Technical Overview

The Φ-method uses a statistical network approach to construct networks of signed relations in four communities. The method relies on the assumption that a statistical over-representation of interactions signals a positive relation and an under-representation signals a negative relation.

This assumption is motivated by the longstanding theoretical argument that individuals with positive relations are more likely to interact.
Summary for Policy Makers

The study's findings have implications for understanding social dynamics and community cohesion. The Φ-method can be used to infer weighted signed relations from interaction data, providing a new tool for researchers and policymakers to study community structure and dynamics.

The inferred signed relations allow us to study pairs and triads of individuals in a new light, and investigate the pairwise homophily, relational triads, and cohesiveness of groups in the communities.
Disclaimer

The above summaries were generated with the assistance of an AI system.

Abstract

Positive and negative relations play an essential role in human behavior and shape the communities we live in. Despite their importance, data about signed relations is rare and commonly gathered through surveys. Interaction data is more abundant, for instance, in the form of proximity or communication data. So far, though, it could not be utilized to detect signed relations. In this paper, we show how the underlying signed relations can be extracted with such data. Employing a statistical network approach, we construct networks of signed relations in four communities. We then show that these relations correspond to the ones reported in surveys. Additionally, the inferred relations allow us to study the homophily of individuals with respect to gender, religious beliefs, and financial backgrounds. We evaluate the importance of triads in the signed network to study group cohesion.

Tags

Related Posts

Quantifying and suppressing ranking bias in a large citation network

Quantifying and suppressing ranking bias in a large citation network

Citation counts for papers from different fields can't be compared directly because they adopt different citation practices. Researchers have proposed various procedures to suppress these biases, but a new statistical framework shows that existing indicators, including the relative citation count, are still biased by paper field and age. A new normalization procedure motivated by the z-score produces much less biased rankings when applied to citation count and PageRank score. The problem of achieving an ideal unbiased ranking of publications remains open.

Read More
Consensus from group interactions: An adaptive voter model on hypergraphs

Consensus from group interactions: An adaptive voter model on hypergraphs

The researchers studied how group interactions affect the emergence of consensus in a spin system. They found that group interactions amplify small initial opinion biases, accelerate the formation of consensus, and lead to a drift of the average magnetization. The model considers groups of agents represented by hyperedges of different sizes in a hypergraph. The heterogeneity of group sizes is controlled by a parameter β. The study aims to understand the impact of β on reaching consensus. The researchers used computer simulations and an analytic approach to study the dynamics of the average magnetization.

Read More
The mobility network of scientists: Analyzing temporal correlations in scientific careers

The mobility network of scientists: Analyzing temporal correlations in scientific careers

The study of scientist mobility is important for knowledge exchange and understanding the career trajectories of scientists. The researchers analyzed 3.5 million career trajectories of scientists using a novel method of higher-order networks. They found strong evidence for temporal correlations at the level of universities, indicating that scientists tend to move between specific institutions. These correlations also exist at the level of countries but not cities. The results have implications for the efficiency of mobility programs and the institutional path dependence of scientific careers.

Read More