Synthia: Scalable Grounded Persona Generation from Social Media Data

TL;DR

Synthia is a scalable framework that generates authentic, high-fidelity personas grounded in social media data, improving alignment with human opinions and fairness across demographics.

Contribution

It introduces a novel method for constructing scalable, realistic personas grounded in social media, with enhanced fairness and preservation of social network structures.

Findings

Outperforms prior methods in aligning with human opinion distributions.

Shows improved fairness across most demographic groups.

Preserves social network structures enabling network-aware analysis.

Abstract

Persona-driven simulations are increasingly used in computational social science, yet their validity critically depends on the fidelity of the underlying personas. Constructing virtual populations that are both authentic and scalable remains a central challenge. We introduce Synthia, a persona-generation framework that grounds LLM-generated personas in real social-media posts while delegating narrative construction to language models, using publicly available data from the Bluesky platform. Across multiple social-survey benchmarks, Synthia improves alignment with human opinion distributions over prior state-of-the-art approaches while relying on substantially smaller models. A multi-dimensional fairness and bias analysis shows that Synthia outperforms previous methods for most demographics across different dimensions. Uniquely, Synthia preserves interaction-graph structure among personas grounded in real social network users, enabling network-aware analysis, which we demonstrate through two homophily-focused case studies. Together, these results position Synthia as a practical and reliable framework for constructing scalable, high-fidelity, and equitable virtual populations.