Large language models improve social network modeling and dynamics
LLMs for Social Network Modeling: From Network Generation to Dynamic Processes
Social and Information NetworksArtificial Intelligence
Summary
Social networks are complicated, with people interacting and sharing opinions in many ways. The authors survey how large language models (LLMs) can represent users, their relationships, and conversations using natural language. These models help simulate how social networks form and evolve, including how information and rumors spread or how opinions change. The paper groups current research into categories based on network creation and dynamic social behaviors, while noting challenges like bias and sensitivity to input. They also outline directions for improving the use of LLMs in social network studies.
What this means in practice
- •For social media platform engineers: Generate realistic simulated user networks to test platform features and content policies that consider language-driven interactions and evolving user behavior.
- •For marketing analytics teams: Model how opinions and information spread through language-rich social networks to improve targeting and campaign design.
A survey. It maps existing work.
Authors
Shikha Mallick, Alex Thomo, Akrati Saxena
Abstract
Large language models (LLMs) are rapidly emerging as a new paradigm for modeling social networks by representing users and their relationships and interactions through natural language. Unlike classical network models or deep learning approaches, LLMs can simulate context-aware social behavior and language-driven interactions, enabling more realistic modeling of network formation and dynamic social processes. However, existing studies are scattered across different research communities and lack a unified perspective. This survey presents the first comprehensive review of LLMs for social network modeling by organizing the literature into two broad categories: network generative models and dynamic process models. Network generative models are further classified into selection-based and interaction-based approaches, while dynamic process models are categorized into opinion dynamics, information diffusion, and rumor propagation, each with their underlying modeling mechanisms. LLMs enable rich textual social interactions and decision-making, but they also exhibit many limitations, including inherent social biases and prompt sensitivity. We outline these open research challenges and discuss future directions in LLM-based social network modeling.