Neural score to measure conceptual understanding
As students learn a new concept, measuring how well they grasp itdepended
on traditional paper and pencil tests. Researchers at Dartmouth College have
developed a machine learning algorithm, which can be used to measure how well a
student understands a concept based on his or her brain activity patterns. The
findings are published in Nature Communications.
The study looks at how knowledge learned in school is represented in the brain. To test knowledge of concepts in STEM(Science, Technology, Engineering, and Math), Dartmouth researchers examined how novices and intermediate learners' knowledge and brain activity compared when testing mechanical engineering and physics concepts, and then developed a machine learning algorithm to get a neural score that assess difference in their conceptual understanding. An engineer and novice will see something different when they look at a photograph of a structure. The results demonstrated that the higher the neural score, the higher the student scored on the concept knowledge tests.