Game players express their values related to self-expression through various means such as avatar customization, gameplay styles, and interactions with other players. Multiplayer online games, now often integrated with social networks, provide social contexts in which player-to-player interactions take place, for example, through the trading of virtual items between players. Building upon a theoretical framework based in computer science and cognitive science, we present results from a novel approach to modeling and analyzing player values in terms of both preferences made in avatar customization, and patterns in social networking use. Our approach resulted in the development of the Steam-Player-Preference Analyzer (Steam-PPA) system, which (1) performs advanced data collection on publicly available social networking profile information and (2) the AIR Toolkit Status Performance Classifier (AIR-SPC), which uses machine learning techniques including clustering, natural language processing, and support vector machines (SVM) to perform inference on the data. As an initial case-study, we apply both systems to the popular, and commercially successful, multi-player first-person-shooter game Team Fortress 2 by analyzing information from player accounts on the social network Steam, together with avatar customization information generated by the player within the game. Our model uses social networking information to predict the likelihood of players customizing their profile in several ways associated with the monetary values of the players' avatar.