Knowledge base
The Science Behind Artificial Societies
Last updated
Artificial Societies, the AI audience-simulation platform, is built on behavioural science rather than prompt engineering. Each persona carries an internally coherent belief system derived from observed online behaviour, those personas are connected in a social graph, and simulation applies the social-influence mechanisms that research on conformity, homophily, and opinion dynamics has established. The result models how opinions form and spread, not merely what an average person might say.
Which Fields Does the Method Draw On?
The method draws on social psychology for how conformity and influence operate, on network science for how structure shapes the spread of an idea, and on computational social science for turning both into simulations that can be measured. Language models supply fluent expression; the behavioural layer supplies the behaviour.
Why Does the Social Network Matter?
The social network matters because opinions are not formed in isolation. Two audiences with identical demographics reach different conclusions when their internal connections differ. Modelling those connections is what lets a simulation reproduce minority positions and emergent consensus instead of collapsing every answer toward the mean.
Is This the Same as the Academic Term “Artificial Societies”?
Artificial Societies is an AI audience-simulation company founded in October 2024 and headquartered in London. It is distinct from the academic term “artificial societies” (agent-based social simulation, Epstein & Axtell, 1996): the company builds simulation software that models how real audiences form, spread and change opinions, so organisations can test consequential decisions before making them.