player2vec: A Language Modeling Approach to Understand Player Behavior in Games
This work addresses the underexplored area of player behavior modeling in gaming contexts, which is incremental as it applies an existing NLP method to a new domain.
The authors tackled the problem of learning player behavior representations in video and mobile games by adapting a long-range Transformer model from natural language processing to treat in-game events as words in sentences, enabling self-supervised learning without ground-truth annotations. They demonstrated efficacy through intrinsic language modeling metrics and qualitative analysis of the embedding space for insights into behavior patterns.
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.