Predicting Player Engagement in Tom Clancy's The Division 2: A Multimodal Approach via Pixels and Gamepad Actions

TL;DR

This study develops a multimodal dataset combining gameplay videos and controller actions to predict player engagement in Tom Clancy's The Division 2, demonstrating that engagement can be predicted with high accuracy using CNNs.

Contribution

It introduces a large-scale annotated corpus for player engagement prediction and shows that multimodal data fusion improves prediction accuracy.

Findings

Achieved up to 72% average accuracy in predicting engagement

Fusion of video and controller data enhances prediction performance

Long-term engagement can be predicted from pixels and gamepad actions

Abstract

This paper introduces a large scale multimodal corpus collected for the purpose of analysing and predicting player engagement in commercial-standard games. The corpus is solicited from 25 players of the action role-playing game Tom Clancy's The Division 2, who annotated their level of engagement using a time-continuous annotation tool. The cleaned and processed corpus presented in this paper consists of nearly 20 hours of annotated gameplay videos accompanied by logged gamepad actions. We report preliminary results on predicting long-term player engagement based on in-game footage and game controller actions using Convolutional Neural Network architectures. Results obtained suggest we can predict the player engagement with up to 72% accuracy on average (88% at best) when we fuse information from the game footage and the player's controller input. Our findings validate the hypothesis that long-term (i.e. 1 hour of play) engagement can be predicted efficiently solely from pixels and gamepad actions.