Aggregation of Action Symbol Sub-sequences for Discovery of Online-Game Player Characteristics Using KeyGraph

Keygraph is a visualization tool for discovery of relations among text-based data. This paper discusses a new application of KeyGraph for discovery of player characteristics in Massively Multiplayer Online Games (MMOGs). To achieve high visualization ability for this application, we propose a preprocessing method that aggregates action symbol sub-sequences of players into more informative forms. To verify whether this aim is achieved, we conduct an experiment where human subjects are asked to classify types of players in a simulated MMOG with KeyGraphs using and not using the proposed preprocessing method. Experimental results confirm the effectiveness of the proposed method.