player2vec: A Language Modeling Approach to Understand Player Behavior in Games

TL;DR

This paper introduces player2vec, a novel Transformer-based method that models player behavior in games by treating in-game events as language tokens, enabling self-supervised learning of player representations.

Contribution

It extends language modeling techniques to gaming data, providing a new way to understand and analyze player behavior without ground-truth labels.

Findings

Effective in modeling behavior event distributions

Learned embeddings reveal meaningful behavior patterns

Supports downstream analysis and insights

Abstract

Methods for learning latent user representations from historical behavior logs have gained traction for recommendation tasks in e-commerce, content streaming, and other settings. However, this area still remains relatively underexplored in video and mobile gaming contexts. In this work, we present a novel method for overcoming this limitation by extending a long-range Transformer model from the natural language processing domain to player behavior data. We discuss specifics of behavior tracking in games and propose preprocessing and tokenization approaches by viewing in-game events in an analogous way to words in sentences, thus enabling learning player representations in a self-supervised manner in the absence of ground-truth annotations. We experimentally demonstrate the efficacy of the proposed approach in fitting the distribution of behavior events by evaluating intrinsic language modeling metrics. Furthermore, we qualitatively analyze the emerging structure of the learned embedding space and show its value for generating insights into behavior patterns to inform downstream applications.