G-Player: Exploratory Visual Analytics for Accessible Knowledge Discovery

Abstract

Understanding player behavior and making sense of gameplay actions is a non-trivial and time-consuming process that requires both thorough domain knowledge of game design, and advanced technical skills in database query languages and statistical packages. Researchers, technology partners and content creators are developing tools to aid in the process of knowledge discovery to gain insights and understanding player behavior. This is important for game production, as it is crucial for formative evaluation of game designs, but is also important for research applications to understand human behavior. In this paper we present G-Player, a tool that aims at democratizing advanced intelligence and knowledge discovery from players’ behavior. G-Player leverages spatial visualizations, such as heat maps and event/movement plotting, to answer complex queries on spatio-temporal data. It allows quick turn-around time between data analysis, hypothesis forming and verification on multimodal datasets, and lets users gain levels of insight beyond simple descriptive statistics. As a first step, we evaluated our tool for production, through domain experts, who were asked to compare it to their current tools. Through this comparison, we enumerate advantages and disadvantages of G-Player’s design as a tool to expand our understanding of player behaviors through space and time analysis.