Modeling and Analyzing Social Networks of Games

• Autor(a) principal: Moraes, Leonardo Mauro Pereira
• Data de Publicação: 2020
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Biblioteca Digital de Teses e Dissertações da USP
• Texto Completo: https://www.teses.usp.br/teses/disponiveis/55/55134/tde-27072020-134224/
• topic: Data mining; Design de jogos; Detecção de influenciadores digitais; Detection of influencers; Game design; Mineração de dados; Modelagem de jogador; Player modeling; Redes social de jogos; Social network of games

Digital games are dynamic environments where the players interact with the games and, commonly, also with other players. The players interactions have many types of relationships, both with other players (e.g., be friend, share games) and with games (e.g., buy, play, like); these relationships can be represented by social networks, i.e., in this context, a Social Network of Games (SNG). During a gameplay, the player produces a vast amount of data continuously: data that represents his/her experiences, preferences and behavioral patterns. In this way, it is possible to use these data to understand the players preferences, i.e., Player Modeling, and to improve the attractiveness of new games. However, this task requires the analysis of a vast amount of data, what is impracticable to do manually, then requiring robust algorithms of a research area named Knowledge Discovery in Databases (KDD) to overcome such an issue. It is possible to apply KDD techniques in data of a SNG to model the players, as well as to identify intrinsic features of the games. This MSc work aimed to explore a real SNG using KDD techniques for identifying common features among popular games, which may represent reasons why the games are popular. However, to achieve this goal, it is necessary to analyze games developed by non-influencer makers, because influencers may receive biased attention in their games that is not necessarily motivated by the game quality. First, we focused on detecting the game influencers to filter them out; empirical experiments show that our approach automatically detects influencers with high precision, even when using data from distinct nationalities for training and testing. Then, we performed a detailed analysis of games features, searching for object combinations that occur in the popular games developed by non-influencer makers, so to support game designers in the elaboration process of new games. This case study introduces a new design pattern for platform games. Also, we present an extensive analysis of object combinations that commonly occur in popular games. All experiments were performed on players and games from the worldwide well-known Super Mario Maker (Nintendo, Kyoto, Japan).