North Carolina State University computer scientists have used World of Warcraft to develop a method for predicting player behavior, which they say is up to 80% accurate and could have applications for developers wanting to tailor future content toward player desires.
“If you have a good idea of what players like, you can make informed decisions about the kind of storylines and mechanics those players would like in the future,” says the study's co-author, Dr. David L. Roberts. ““This work could obviously be used for World of Warcraft or other MMORPGs, but it also applies to any setting where users are making a series of decisions. That could be other gaming formats, or even online retailing.”
The study will be detailed in a paper, “Using Sequential Observations to Model and Predict Player Behavior.” Roberts and fellow author Brent Harrison will present the paper at France's Foundations of Digital Games Conference at the end of the month. Their method involved breaking down player achievements into “cliques,” noting that players who fulfilled one criteria tended to also fulfill the others in the “clique.” This, they say, leads to a highly accurate method of predicting a player's actions in-game, allowing designers to cater to what they believe players will want to do.
Could, say, Okami or LA Noire have come out of this method of giving players what they want? Will games benefit from designers taking a more deterministic view of how players will respond to the worlds they create? Free-will gamers, represent!
Jun 20, 2011
Study: Racing games help players learn to drive... just not safely
Is that a good statistic?
Study: Gaming skills improved through mild shocks to the head
Centuries old electric technique shown to increase cognitive functions