Improving Deep Localized Level Analysis: How Game Logs Can Help

TL;DR

This paper introduces a deep CNN approach for affect prediction in games, leveraging game logs and level structure data to improve accuracy and enable cross-domain player modeling.

Contribution

It presents a novel deep learning method that combines game logs and level structure for better affect prediction and cross-domain applicability.

Findings

Outperforms previous affect prediction methods.

Training on game logs enhances cross-domain player modeling.

Effective on levels from multiple Mario game variants.

Abstract

Player modelling is the field of study associated with understanding players. One pursuit in this field is affect prediction: the ability to predict how a game will make a player feel. We present novel improvements to affect prediction by using a deep convolutional neural network (CNN) to predict player experience trained on game event logs in tandem with localized level structure information. We test our approach on levels based on Super Mario Bros. (Infinite Mario Bros.) and Super Mario Bros.: The Lost Levels (Gwario), as well as original Super Mario Bros. levels. We outperform prior work, and demonstrate the utility of training on player logs, even when lacking them at test time for cross-domain player modelling.