Is it possible to predict the motivation of players just by observing their gameplay data? Even if so, how should we measure motivation in the first place? To address the above questions, on the one end, we collect a large dataset of gameplay data from players of the popular game Tom Clancy's The Division. On the other end, we ask them to report their levels of competence, autonomy, relatedness and presence using the Ubisoft Perceived Experience Questionnaire. After processing the survey responses in an ordinal fashion we employ preference learning methods based on support vector machines to infer the mapping between gameplay and the reported four motivation factors. Our key findings suggest that gameplay features are strong predictors of player motivation as the best obtained models reach accuracies of near certainty, from 92% up to 94% on unseen players.
At Massive Enternatainment they were interested in the question of which basic psychological needs are satisfied by different video games? And what makes a game actually fun to play?
To answer these questions, Massive Entertainment has developed a questionnaire called “Ubisoft Perceived Experience Questionnaire” (UPEQ). The questionnaire is based on a model called Self-Determination Theory, and reveals how each individual player is driven by a different configuration of these factors: competence, autonomy, relatedness and presence. Massive Entertainment, working together with the Institute of Digital Games team composed of David Melhart, Dr Antonios Liapis, and Prof Georgios Yannakakis, author of the quintessential textbook on AI in Games they found a way to predict player motivations based solely on gameplay behavior and the questionnaire responses from a handful of players, at almost certainty levels. The research has been accepted for IEEE Conference on Games in 2019 and the details can be accessed here.
In brief the paper entitled Your Gameplay Says It All: Modelling Motivation in Tom Clancy's The Division is innovative for four main reasons. First this is the first time player motivation (as in self-determination) is modelled computationally only through gameplay data in games. Second, the ordinal approach used in the study compares the subjective scores of all players with each other and hence generates combinatorially very large datasets based only on small sets of participants. Third, we model aspects of player motivation using preference learning based solely on a small number of key gameplay features, so to achieve this level of accuracy a large training set is not required. And finally, for the first time we evaluate the method in Tom Clancy’s The Division (Ubisoft, 2016) on a large set of players and the predictive capacity of the motivation models for this game reach near certainty (i.e., over 80% of average accuracy).
The Institute operates on the cutting edge of videogame AI research in addition to a wide spectrum of other game-related research. If you want to stay up to date with research such as this one subscribe to our Newsletter. We also host a number of public events and lectures and by subscribing to our Newsletter you will be automatically notified of these as well.