The Developers Of Division 2 Now Know What Motivates You For A Long Time

The Developers Of Division 2 Now Know What Motivates You For A Long Time

The developers of The Division 2 use data science and machine learning to create better games.

In a blog post by Massive Entertainment, the developers of The Division and The Division 2, senior user researcher and data scientist Alessandro Canossa speak up. He asks the question in the room “What makes you like to play a game?”

Because at Massive, so Canossa, do not just develop games. Explore and use various innovative technologies and tools to understand what motivates players to play the games.

“Fun” is not the same for everyone

What motivates players? Canossa explains that every developer wants to create a game that is fun. But fun is not the same for everyone. Therefore, he is working on a project that should make it possible to predict only because of the gameplay behavior of different players, which motivates them to a game.

In other words, he explores the psychological needs of different games and what makes a game fun.

Who works on the project? Canossa himself was Associate Professor at the University of Boston, where he worked in the growing field of gaming analytics. Due to his academic background, he was able to team up with former colleagues at the Institute for Digital Games at the University of Malta to advance this project.

The project should be able to collect data from millions of players

Questionnaires gather only a few data: In order to find out what makes a game fun for gamers, Massive first developed a specific questionnaire. This is based on the self-determination theory and outlines how much the players are driven by the following factors: competence, autonomy, social inclusion, and attitude.

But no matter how good a questionnaire is, it’s difficult to gather in-depth feedback from millions of players.

Innovative technologies instead of questionnaires: That’s why, according to Canossa, we now use innovative machines that learn specific techniques to predict player motivation based solely on gameplay behavior.

This technological advance alone is unbelievable, but now you can not only evaluate the motivation data of a couple of hundred players who completed the questionnaire but also leverage the data of millions of players out there for future games.

This is how the player motivation can be predicted

Machines must first learn: Data was used, which the researchers collected from around 300 voluntary The Division players. These were run through a specific learning algorithm.

By processing game data, game styles, and the questionnaire, the algorithm was continually taught how to measure the dedication and motivation of the players.

After the learning phase, the algorithm can predict how a player feels – depending on his or her competence, autonomy, social involvement, and attitude. Only on the basis of the gameplay data is the algorithm supposed to have an accuracy of 97%.

The gameplay of players with a high level of competence differs significantly from players who are less competent. This can also be detected with the naked eye. However, there are still many gradations in between, which are not so obvious to observe.

And it turned out to be tricky to want to determine motivational factors only by means of in-game actions.

The technique can do it: The machine, however, is now able to predict the complex, psychological constructs in all its nuances on the basis of the gameplay.

The success of this project shows that it’s possible to leverage gameplay data, combine it with survey-based insights to map complex emotional and cognitive states.

Better games are possible: Ubisoft will make this deeper knowledge about the consumers fruitful, in order to deliver better and more personalized gameplay experiences in the future.

The new clan system in Division 2 may motivate you to achieve goals together with your friends.

Stay Tuned For More Updates