Adaptive Robotic Tutors that Support Self-Regulated Learning: A Longer-Term Investigation with Primary School Children

Aidan Jones,Ginevra Castellano

doi:10.1007/s12369-017-0458-z

Aidan Jones, Ginevra Castellano

Open Access

https://doi.org/10.1007/s12369-017-0458-z

Copy DOI

Abstract

Robots are increasingly being used to provide motivating, engaging and personalised support to learners. These robotic tutors have been able to increase student learning gain by providing personalised hints or problem selection. However, they have never been used to assist children in developing self regulated learning (SRL) skills. SRL skills allow a learner to more effectively self-assess and guide their own learning; learners that engage these skills have been shown to perform better academically. This paper explores how personalised tutoring by a robot achieved using an open learner model (OLM) promotes SRL processes and how this can impact learning and SRL skills compared to personalised domain support alone. An OLM allows the learner to view the model that the system holds about them. We present a longer-term study where participants take part in a geography-based task on a touch screen with adaptive feedback provided by the robot. In addition to domain support the robotic tutor uses an OLM to prompt the learner to monitor their developing skills, set goals, and use appropriate tools. Results show that, when a robotic tutor personalises and adaptively scaffolds SRL behaviour based upon an OLM, greater indication of SRL behaviour can be observed over the control condition where the robotic tutor only provides domain support and not SRL scaffolding.

Highlights

Self-Regulated Learning (SRL) skills are seen as increasingly relevant and essential for the 21st Century [42,46] as they are significantly correlated with measures of academic performance [55]
Adherence to Ideal SRL Model: moving to a more difficult activity when an activity is mastered The chart in Fig. 5 shows the average number of times the learners in each condition follow the ideal model of SRL by moving on to a more difficult activity when the current activity is mastered in each session
We see that the SRL condition learners on average have a higher adherence to the model and this increases over the sessions

Summary

Introduction

Self-Regulated Learning (SRL) skills are seen as increasingly relevant and essential for the 21st Century [42,46] as they are significantly correlated with measures of academic performance [55]. SRL is the meta-cognitive process where a student uses self-assessment, goal setting, and the selecting and deploying of strategies to acquire academic skills [55] By supporting these skills students may be able to learn more effectively, even outside of the tutoring session. To be effective in long-term interactions the robot should be able to display an awareness of, and respond to, the user’s affective state and adapt to the individual’s preferences in order to build and maintain a good social interaction [29] Another way to build a bond between the robot and learner is to use memory to recall past activities [28]. This enables us to see if the skills developed by a learner can transfer to long-term behaviour change [51] or generalise to other scenarios and contexts [5]

Objectives

Methods

Results

Discussion

Conclusion