Virtual tutors: NC State receives grant to study artificial intelligence in the classroom

September 16, 2010

While some students might dream of having a robot to help them with their homework, researchers at North Carolina State University are getting closer to making it happen.

NC State recently received a four-year, $3.5 million grant to explore using artificial intelligence as a learning tool inside fourth- and fifth-grade science classrooms. Artificial intelligence is the science of giving computers human-like abilities to understand, plan, communicate, perceive, etc.

The project includes creating "CyberPads" - computer notebooks with artificial intelligence-based software that allows the user to create graphical representations that model different scientific phenomena they learn in the classroom.

"Fourth- and fifth-grade science classes have a particular focus on physical and earth sciences. The CyberPads will support interactive scientific modeling for topics such as electricity, landforms, weather and climate," explains Dr. James Lester, NC State professor of computer science and the project's principal investigator. "Students will actually be able to sketch out these different concepts using the program, and then see the models come to life with animation, sound and narration."

Assisting the students in using the CyberPads will be "PadMates" - or intelligent virtual tutors that support science learning through interactive scientific modeling. The PadMates will be able to recognize the understanding of the student using the CyberPad and interact with them accordingly. For instance, a student struggling to grasp the concept of gravity would receive more detailed explanations and assistance than a student who quickly exhibits his or her understanding of the topic.

"Today's teachers are tasked with trying to provide focused instruction for each student in their classroom. And in a classroom with potentially 25 students at different points along a learning progression for any given science topic, you can see how extremely difficult - if not impossible - it is to give that sort of individualized attention," explains Dr. Eric Wiebe, NC State associate professor of math, science and technology education, and co-principal investigator on the project. "For years, studies have shown the important role one-on-one tutoring plays in a child's understanding - so using 'virtual' tutors will provide teachers important assistance."

The program will initially be rolled out in 16 fourth- and fifth-grade science classrooms in North Carolina, to be followed by an additional 44 classrooms in Texas and California. As part of the program, professional development will be given to the teachers in order to prepare them to use CyberPads and PadMates in their classrooms as effective teaching tools. Researchers will study the students' problem solving skills - such as strategy, thinking and collaboration - as well as the level of engagement in learning the science concepts before and after the use of CyberPads to see if, and how, the tools impact learning.

"Beyond supporting teaching overall science content knowledge, this system will also help students get creative in their problem-solving skills. This isn't just repeating back something they heard from their teacher - they'll actually be demonstrating an understanding of some very specific concepts," Lester says.
-end-
The project, "The Leonardo Project: An Intelligent Cyberlearning System for Interactive Scientific Modeling in Elementary Science Education," is funded by the National Science Foundation's Discovery Research K-12 program. In addition to Lester and Wiebe, the NC State project team includes Dr. Mike Carter, associate dean of the graduate school, and Dr. Bradford Mott, computer research scientist.

North Carolina State University

Related Learning Articles from Brightsurf:

Learning the language of sugars
We're told not to eat too much sugar, but in reality, all of our cells are covered in sugar molecules called glycans.

When learning on your own is not enough
We make decisions based on not only our own learning experience, but also learning from others.

Learning more about particle collisions with machine learning
A team of Argonne scientists has devised a machine learning algorithm that calculates, with low computational time, how the ATLAS detector in the Large Hadron Collider would respond to the ten times more data expected with a planned upgrade in 2027.

Getting kids moving, and learning
Children are set to move more, improve their skills, and come up with their own creative tennis games with the launch of HomeCourtTennis, a new initiative to assist teachers and coaches with keeping kids active while at home.

How expectations influence learning
During learning, the brain is a prediction engine that continually makes theories about our environment and accurately registers whether an assumption is true or not.

Technology in higher education: learning with it instead of from it
Technology has shifted the way that professors teach students in higher education.

Learning is optimized when we fail 15% of the time
If you're always scoring 100%, you're probably not learning anything new.

School spending cuts triggered by great recession linked to sizable learning losses for learning losses for students in hardest hit areas
Substantial school spending cuts triggered by the Great Recession were associated with sizable losses in academic achievement for students living in counties most affected by the economic downturn, according to a new study published today in AERA Open, a peer-reviewed journal of the American Educational Research Association.

Lessons in learning
A new Harvard study shows that, though students felt like they learned more from traditional lectures, they actually learned more when taking part in active learning classrooms.

Learning to look
A team led by JGI scientists has overhauled the perception of inovirus diversity.

Read More: Learning News and Learning Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.