Artificial Societies uses networks of AI personas to simulate high-value audiences, used by Fortune 100 organisations to test how strategies shift opinions that matter. Here's how AS models human opinion, and how it performs against human panels and simple synthetic personas.
The standard approach of creating a synthetic persona is by prompting an LLM with an invented biography (e.g, "you are a 34-year-old teacher from Ohio"), which produces generic, stereotyped answers.
Artificial Societies is different. We employ a unique and proprietary approach, developed over years of research originating from the first large-scale AI society paper. This approach combines real-world intelligence gathering, the mapping of individual belief systems, and a unique network science modelling method.
Rich psychographic profiles, built from anonymised, real-world observations.
Personas are placed in a network that captures real-world social influence.
Belief systems and network systems combine to model opinion at every level.
Artificial Societies accurately capture human opinion distributions, and every individual response is interpretable with why they answered as they did.
Artificial Societies' surveys have been compared with 1,000 large-scale survey questions on different populations and opinion topics. In addition to top-line distribution accuracy, we also measure the multiple levels of realism that matter for consequential decisions.
How much simulated opinions overlap with human panels, compared to how much human opinions self-replicate.
What this means: Reliably test how a decision shifts opinion.
How often participants contradict themselves — AS personas stay focused better than human respondents.
What this means: Higher-quality signal on high-value audiences.
Alignment amongst questions about the same underlying attitudes (Cronbach's α). Human panels span 60-95%; acceptable quality starts at 70%.
What this means: Valid relationships between opinions, required for critical strategies.
Distinct-word richness in a typical open-text response, benchmarked against 120,000 human social-media posts.
What this means: Open-ended answers with human-level nuance.
Artificial Societies is unique beyond digital twins and synthetic populations.