Link Prediction and the Role of Stronger Ties in Networks of Face-to-Face Proximity

TL;DR

This paper investigates link prediction in face-to-face contact networks, analyzing how stronger ties influence link formation and comparing different proximity measures to enhance understanding of network dynamics.

Contribution

It introduces a comparative analysis of neighborhood and path-based proximity measures and explores the impact of stronger ties on link predictability in face-to-face networks.

Findings

Stronger ties significantly influence link formation.

Neighborhood-based measures outperform path-based measures in prediction.

Insights support improved human contact network recommendations.

Abstract

Understanding the structures why links are formed is an important and prominent research topic. In this paper, we therefore consider the link prediction problem in face-to-face contact networks, and analyze the predictability of new and recurring links. Furthermore, we study additional influence factors, and the role of stronger ties in these networks. Specifically, we compare neighborhood-based and path-based network proximity measures in a threshold-based analysis for capturing temporal dynamics. The results and insights of the analysis are a first step onto predictability applications for human contact networks, for example, for improving recommendations.