From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media

TL;DR

This paper introduces behavioral traits into generative agent-based models to better simulate diverse and realistic social media behaviors, improving the modeling of information spread and user interaction patterns.

Contribution

It proposes a new layer of behavioral traits for agents in GABM, enabling differentiated engagement and more accurate social media simulations.

Findings

Behavioral traits are crucial for heterogeneous participation patterns.

Profiles influence content propagation dynamics.

Simulation results align with real-world social media data.

Abstract

Generative Agent-Based Modeling (GABM) leverages Large Language Models to create autonomous agents that simulate human behavior in social media environments, demonstrating potential for modeling information propagation, influence processes, and network phenomena. While existing frameworks characterize agents through demographic attributes, personality traits, and interests, they lack mechanisms to encode behavioral dispositions toward platform actions, causing agents to exhibit homogeneous engagement patterns rather than the differentiated participation styles observed on real platforms. In this paper, we investigate the role of behavioral traits as an explicit characterization layer to regulate agents' propensities across posting, re-sharing, commenting, reacting, and inactivity. Through large-scale simulations involving 980 agents and validation against real-world social media data, we demonstrate that behavioral traits are essential to sustain heterogeneous, profile-consistent participation patterns and enable realistic content propagation dynamics through the interplay of amplification- and interaction-oriented profiles. Our findings establish that modeling how agents act-not only who they are-is necessary for advancing GABM as a tool for studying social media phenomena.