Guidelines for Designing Social Robots as Second Language Tutors

Abstract

In recent years, it has been suggested that social robots have potential as tutors and educators for both children and adults. While robots have been shown to be effective in teaching knowledge and skill-based topics, we wish to explore how social robots can be used to tutor a second language to young children. As language learning relies on situated, grounded and social learning, in which interaction and repeated practice are central, social robots hold promise as educational tools for supporting second language learning. This paper surveys the developmental psychology of second language learning and suggests an agenda to study how core concepts of second language learning can be taught by a social robot. It suggests guidelines for designing robot tutors based on observations of second language learning in human-human scenarios, various technical aspects and early studies regarding the effectiveness of social robots as second language tutors.

Keywords: Human–robot interaction; Robot tutor; Second language learning; Social robot.

Fig. 1

Mean accuracy scores on the direct post-test (top) and the delayed post-test (bottom). Purple bars refer to the object condition; orange bars to the tablet condition. Reprinted from [68]. (Color figure online)

Fig. 2

The L2TOR setup includes the NAO robot standing to the side of the child with a tablet in between them

Fig. 3

Pronunciation ratings from seven German native speakers for 5 child participants. Three of the children improve over the course of the interaction, although one child has initially accurate pronunciation that drops over time, possibly due to fatigue

Fig. 4

Mean duration per gaze to the robot, blocks, experimenter, and elsewhere for the three feedback conditions

Fig. 5

Mean numbers of correct answers at the beginning (first 7) and end (last 7) of the interaction in the different conditions. Adapted from [61]

Fig. 6

Participant-wise amount of correct answers grouped by the different conditions for the L1-to-L2 post-test. Adapted from [61]