A Simulation Framework for Studying Recommendation-Network Co-evolution in Social Platforms

TL;DR

This paper introduces an agent-based simulation framework to study how recommendation systems influence social network evolution, validated with real platform data, and explores how timing and scale affect network outcomes.

Contribution

It presents a novel simulation environment for analyzing recommendation-network co-evolution, calibrated with Mastodon data and validated against Bluesky, enabling controlled experiments.

Findings

Activation timing impacts network structure and engagement.

Delaying recommendations increases content diversity.

Effects persist but diminish as network size grows.

Abstract

Studying how recommendation systems reshape social networks is difficult on live platforms: confounds abound, and controlled experiments risk user harm. We present an agent-based simulator where content production, tie formation, and a graph attention network (GAT) recommender co-evolve in a closed loop. We calibrate parameters using Mastodon data and validate out-of-sample against Bluesky (4--6\% error on structural metrics; 10--15\% on held-out temporal splits). Across 18 configurations at 100 agents, we find that \emph{activation timing} affects outcomes: introducing recommendations at $t=10$ vs.\ $t=40$ decreases transitivity by 10\% while engagement differs by $<$8\%. Delaying activation increases content diversity by 9\% while reducing modularity by 4\%. Scaling experiments ($n$ up to 5,000) show the effect persists but attenuates. Jacobian analysis confirms local stability under bounded reactance parameters. We release configuration schemas and reproduction scripts.