Sociolinguistic methods improve persona style in user simulations
Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation
Computation and Language
Summary
It is hard to make simulated users talk like real people, and the usual ways to check this are slow and subjective. The authors test a new method that looks at how people speak, focusing on consistent style rather than just descriptions. This approach uses well-known language analysis techniques to check if the simulated users keep their style. They found it works better than previous methods at making and measuring believable user speech patterns, though being stylistically accurate doesn’t always mean sounding completely natural.
What this means in practice
- •For customer service teams: Assess and improve chatbot responses by measuring how closely simulated user language matches real customer styles, making service testing more reliable.
- •For dialogue system developers: Create more diverse user personas for testing dialogue agents by authoring stylistic profiles that can be quantitatively evaluated for fidelity.
Authors
Lex Konnelly, Elena Khasanova, Riqiang Wang, Matthias Lee, Harsh Saini, Parsa Kavehzadeh
Abstract
As agentic systems gain commercial popularity, user simulators increasingly serve as measurement instrument for their evaluation. However, the fidelity of simulated users in comparison to real human users is generally low, and typically assessed by costly, subjective LLM judges. In this pilot study, we ask whether fidelity can instead be measured deterministically by treating a user persona sociolinguistically: as a social type that emerges from observable linguistic style, rather than one predicted by labels or descriptions a model must extrapolate into behaviour. We author personas as concrete stylistic rates, which lets us transfer two established, model-free instruments -- authorship-verification stylometry and lexicon-based content analysis -- as fidelity diagnostics. We A/B-test the sociolinguistic schema against a flat descriptive baseline across five task-oriented customer-service agents. Results show that the sociolinguistic schema improves both stylistic adherence and stylometric distinguishability for most of the tested models, with a caveat that persona style fidelity does not necessarily equal persona "naturalness". We argue that a sociolinguistic approach to persona design is a promising path towards more diverse and representative user personas, and that these metrics are most valuable in an error-attribution analysis, localizing where fidelity breaks down. This is a first step towards interventions that move user simulations closer to faithful renderings of diverse and variable linguistic outputs.