Abstract
Personalized learning has a higher impact on students' progress than traditional approaches. However, current resources required to implement personalization are scarce. This research aims to conceptualize and develop an autonomous robot tutor with personalization policy for preschool children aged between three to five years old. Personalization is performed by automatically adjusting the difficulty level of the lesson delivery and assessment, as well as adjusting the feedback based on the reaction of children. This study explores three child behaviors for the personalization policy: (i) academic knowledge (measured by the correctness of the answer), (ii) executive functioning of attention (measured by the orientation and the gaze direction of child's body), and (iii) working memory or hesitation (measured by the time lag before the answer). Moreover, this study designed lesson content through interviews with teachers and deployed the personalization interaction policy through the NAO robot with five children in a case user study method. We qualitatively analyze the session observations and parent interviews, as well as quantitatively analyze knowledge gain through pre- and posttests and a parent questionnaire. The findings of the study reveal that the personalized interaction with the robot showed a positive potential in increasing the children's learning gains and attracting their engagement. As general guidelines based on this pilot study, we identified additional personalization strategies that could be used for autonomous personalization policies based on each child's behavior, which could have a considerable impact on child learning.