Better learning impact
This device was tested subsequently with three groups ofstudents. One of them studied an old Japanese story with the helpof an engaging Wakamaru robot. The other two groups were taught thesame story by a non- or randomly-engaging robot. The group learningwith a mind-reading robot scored on average 9 out 14 points on asubsequent tests, while non-engaged students scored a 6.3.
Andrew Ng, director at Stanford’s Artificial Intelligence Lab inCalifornia, commented: “One-on-one tutoring has been repeatedlyshown to give dramatic results in student learning, but the mainproblem with it is the cost, and that it’s just difficult to scale.The vision of automatically measuring student engagement so as tobuild a more interactive teacher is very exciting.”