Adaptive Learning Project Uses Video Games in the Classroom

An easier and more cost-effective way to introduce science curriculum into the classroom is in development that could involve playing video games.

Created by Washington State University professor Richard Lamb, “computational modeling” involves a computer “learning” student behavior and then “thinking” as the student would.

“Traditionally, we’d be confined to a classroom to study student learning for virtually every potential theory we have about science education and curriculum implementation,” Lamb said.

“But now, instead of taking a shotgun approach, we can test the initial interventions on a computer and see which ones make the most sense to then study in the classroom,” he said.

The method allows for a more clearly targeted in-person research with less participants, saving time and money for researchers.

“In the current model of research, we go into a classroom and spend months observing, giving tests and trying to see if changes to a specific model work and how to best implement them,” Lamb said. “It will still be necessary for researchers to go into the classroom; hopefully that never goes away. This just gives us more flexibility.”

To complete his research, Lamb uses an artificial neural network he and fellow researchers named the Student Task and Cognition Model.

Students were asked to play an electronic game that required certain scientific tasks to be completed by making a choice.  Statistical techniques were used to track decisions as a success or failure.

“The computer is able to see what constitutes success, but it’s also able to see how students approach science,” Lamb said.

According to Lamb, the computer is learning how students approach science.  Therefore, it will attempt to solve future problems the same way a student might.

Any video games can be used – Halo, Mario Kart, and others – so long as they are asking for a singular task to be performed.

“The computer is learning to solve novel or new problems, which means we can test different educational interventions before ever getting to a classroom,” he said.

The initial tests will not only let researchers know if a specific educational model will work, it will also offer a rate of success for the model.  Previously, several models would have to be run, wasting time.  Now researchers will be able to choose the model that looks like it will statistically have the best chance of success.

And that translates into savings.

“For me to get 100,000 students, teachers to administer tests, professors doing research and all the rest, we could easily look at about $3.5 million,” Lamb said. “We can now get those 100,000 students for the cost of running software off a computer.”