AI to measure outcome of educational games in learning
Researchers at the University of North Carolina have designed an artificial intelligence model that is better able to predict the outcome of using educational games in learning. The improved model makes use of an AI training concept called multi-task learning and could be used to improve both instruction and learning outcomes. The researchers had gameplay and testing data from 181 students. The AI could look at each student's gameplay and at how each student answered Question 1 on the test. By identifying common behaviours of students who answered Question 1 correctly, and common behaviours of students who got Question 1 wrong, the AI could determine how a new student would answer Question 1. The finding opens the door to incorporating more complex modelling techniques into educational software- particularly educational software that adapts to the needs of the student, according to Andrew Emerson, co-author of the paper.