Visitors play ''World of Warcraft'' at their exhibition stand at the Gamescom 2010 fair in Cologne
Visitors play ''World of Warcraft'' at their exhibition stand at the Gamescom 2010 fair in Cologne August 19, 2010. REUTERS

In 2000, Mel Gibson found out what women want in the movie What Women Want.

In 2011, researchers from North Carolina University have developed a method to find out what video game players want - when they're playing their games. The method, researchers say, can accurately predict the behavior of players in online role-playing games.

We are able to predict what a player in a game will do based on his or her previous behavior, with up to 80 percent accuracy, Brent Harrison, a Ph.D. student at NC State and co-author of the paper describing the research said in a statement.

The research team used a data-driven predictive method by analyzing the behavior of 14,000 players in the massively multiplayer online role-playing game (MMORPG) World of Warcraft. In World of Warcraft, the researchers collected data in which order did players receive their achievement badges. They identified the degree to which each individual achievement was correlated to every other achievement.

From there, the researchers grouped closely correlated achievements together into cliques. They thought those cliques could be used to predict player behavior. If a player achieved four out of seven achievements in a clique, there was a good chance they would go after the other three.

The research could be useful to help publishers develop new game content, or help players go to the parts of a game they will enjoy most.

A good game stands on its own. If you want to improve it, you have to make sure players will like any changes you make. This research can help researchers get it right, because 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, Dr. David L. Roberts, an assistant professor of computer science at NC State and co-author of the paper, said in a statement.

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, he added.

The researchers plan on presenting the paper, Using Sequential Observations to Model and Predict Player Behavior, at the Foundations of Digital Games Conference in Bordeaux, France on June 29.

Follow Gabriel Perna on Twitter at @GabrielSPerna