Categorical Clustering Applied to the Discovery of Character Builds in TCTD2: the BaT Approach
David Renaudie, Robert Lizatovic, Ahmad Azadvar, Rickard Elmqvist, Klaus Hofmeister, Bjorn Kristmannsson · 2020 IEEE Conference on Games (CoG) · 2020
This article describes an attempt to categorize character configurations of players of Tom Clancy's the Division 2, conducted to highlight behavioral differences in approach to gameplay based on one's character build. Nine distinct character builds were extracted for maximum coherence and minimum variance and each build showed significant differences in separate measures of behavior such as playtime, character health and armor among other attributes. The proposed method was also able to recover builds recognized by social forums as well as discovering new ones. Appropriation of Character builds as categorical text-based data (BaT: Build as Text), provides a unique opportunity for game researchers to use a diverse set of input data which will in turn contribute to the improvement of the process of game design informed by player choices. Longitudinal observations in interconnection of obtained clusters may provide further insight into formation and evolution of gameplay types.