# Predicting Personas Using Mechanic Frequencies and Game State Traces

arXiv: https://arxiv.org/abs/2203.13351 · HTML: https://mlsanity.com/paper/2203.13351/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 9 of 9)

- [Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics](https://mlsanity.com/paper/1802.06881/) (2018)
- [Rotation, Translation, and Cropping for Zero-Shot Generalization](https://mlsanity.com/paper/2001.09908/) (2020)
- [Mech-Elites: Illuminating the Mechanic Space of GVGAI](https://mlsanity.com/paper/2002.04733/) (2020)
- [Generating Levels That Teach Mechanics](https://mlsanity.com/paper/1807.06734/) (2018)
- [Intentional Computational Level Design](https://mlsanity.com/paper/1904.08972/) (2019)
- [Mario Level Generation From Mechanics Using Scene Stitching](https://mlsanity.com/paper/2002.02992/) (2020)
- [AtDelfi: Automatically Designing Legible, Full Instructions For Games](https://mlsanity.com/paper/1807.04375/) (2018)
- [Automatic Mapping of NES Games with Mappy](https://mlsanity.com/paper/1707.03908/) (2017)
- ["Press Space to Fire": Automatic Video Game Tutorial Generation](https://mlsanity.com/paper/1805.11768/) (2018)

## Built on by (most cited first, 2 of 2)

- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [Persona-driven Dominant/Submissive Map (PDSM) Generation for Tutorials](https://mlsanity.com/paper/2204.05217/) (2022)

## Abstract (arXiv)

We investigate how to efficiently predict play personas based on playtraces. Play personas can be computed by calculating the action agreement ratio between a player and a generative model of playing behavior, a so-called procedural persona. But this is computationally expensive and assumes that appropriate procedural personas are readily available. We present two methods for estimating player persona, one using regular supervised learning and aggregate measures of game mechanics initiated, and another based on sequence learning on a trace of closely cropped gameplay observations. While both of these methods achieve high accuracy when predicting play personas defined by agreement with procedural personas, they utterly fail to predict play style as defined by the players themselves using a questionnaire. This interesting result highlights the value of using computational methods in defining play personas.