Inferring Player Personality Through Gameplay Telemetry in Unreal Engine

Keywords:
Telemetry, Player Preferences, Trackers, Adaptive Systems, Player Behaviour

Abstract:
Gameplay telemetry is tracked by most modern games, and the data provided could be the key to understanding the correlation between in game behaviour and real world preferences. Player motivation has been studied for decades, but the focus has been more on how motivation translates to in game behaviour. The goal of this study is to discover whether the same can be found the other way around, and whether the previously modelled types offer meaningful guidance on how to comprehend the connections between the two. A scaling system was proposed for inferring players’ preferences using Unreal Engine with a telemetry plug in that records player actions, locations, and custom events. The prototype is made using trackers with thresholds to map preferences in a small open world game with interactable characters. The prototype illustrated how trackers could help the game adapt to behavioural differences and suggested the potential for inferring preferences. The design shows how thresholds may adapt to player type and improve the trackers’ logic. The study revealed the preliminary scoring system for the preference interface, a telemetry based method for mapping player tendencies. The possibility for future research has also been demonstrated.

CITATION:

IEEE format

Copy to clipboard

J. Lončar, A. Busić, A. Bakić, A. Petrović, “Inferring Player Personality Through Gameplay Telemetry in Unreal Engine,” in Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2026, pp. 607-612. doi:10.15308/Sinteza-2026-607-612

APA format

Copy to clipboard

Lončar, J., Busić, A., Bakić, A., Petrović, A. (2026). Inferring Player Personality Through Gameplay Telemetry in Unreal Engine. Paper presented at Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2026-607-612

BibTeX format
Download

RefWorks Tagged format
Download