A Longitudinal Study of Child Wellbeing Assessment via Online Interactions with a Social Robot

TL;DR

This study investigates whether online mediated interactions with a social robot can be used to longitudinally assess the mental wellbeing of children aged 8–13 (N=40) across three sessions. Using the Nao robot and measures including SMFQ and RCADS (robot-administered, self-reported, and parent-reported), the authors show that online interactions differentiate wellbeing levels and that children’s perception of the robot remains stable or improves over time. The work demonstrates that remote robot-mediated assessments can achieve actionable insights with comparable validity to in-lab approaches and reveals gender-specific patterns in wellbeing assessment and robot perception. These findings suggest a scalable, accessible pathway for routine child wellbeing monitoring that can complement clinical practice while highlighting ethical and embodiment considerations for future adaptive systems.

Abstract

Socially Assistive Robots are studied in different Child-Robot Interaction settings. However, logistical constraints limit accessibility, particularly affecting timely support for mental wellbeing. In this work, we have investigated whether online interactions with a robot can be used for the assessment of mental wellbeing in children. The children (N=40, 20 girls and 20 boys; 8-13 years) interacted with the Nao robot (30-45 mins) over three sessions, at least a week apart. Audio-visual recordings were collected throughout the sessions that concluded with the children answering user perception questionnaires pertaining to their anxiety towards the robot, and the robot's abilities. We divided the participants into three wellbeing clusters (low, med and high tertiles) using their responses to the Short Moods and Feelings Questionnaire (SMFQ) and further analysed how their wellbeing and their perceptions of the robot changed over the wellbeing tertiles, across sessions and across participants' gender. Our primary findings suggest that (I) online mediated-interactions with robots can be effective in assessing children's mental wellbeing over time, and (II) children's overall perception of the robot either improved or remained consistent across time. Supplementary exploratory analyses have also revealed that the gender of the children affected their wellbeing assessments with interactions effectively distinguishing between varying levels of wellbeing for both boys and girls for the first session and only for boys during the second session. The analyses have also revealed that girls have a higher opinion of the robot as a confidante as compared with boys. Findings from this work affirm the potential of using online mediated interactions with robots for the assessment of the mental wellbeing of children.

Figures (6)

• Figure 1: (a) Pipeline showing the procedure for mental wellbeing assessment of children in the UK ford2020datamansfield2020oxwellburn2022developing. This pipeline is representative of certain assessment scenarios and is not standardised across all clinical and research assessments conducted in the UK. (b) Proposed robotised mental health assessment pipeline.
• Figure 2: (a) Researcher view of the experimental setup, (b) Participant view of the interaction.
• Figure 3: (a) Longitudinal changes in wellbeing (RCADS scores: dependent variables) across different population groups (overall, girls and boys) categorised into wellbeing tertiles (low, med and high; independent variables) using the SMFQ responses. (b) Children's wellbeing (RCADS scores) across tertiles for all sessions combined. $*p<0.05$ corrected.
• Figure 4: RCADS responses (dependent variables) across session 1 for the different modes of test administration from all population groups categorised into wellbeing tertiles (low, med and high; independent variables) using the SMFQ responses. $*p<0.05$ corrected.
• Figure 5: (a) Longitudinal changes in children's anxiety measurement attributed to the robot across all population groups (overall, girls and boys) categorised into wellbeing tertiles (low, med and high) using the SMFQ responses. (b) Gender-based variability in the role of the robot as a confidante in the remote study. (c) Total percentage of the population that had consistent or improved user perception. User perception changes across tertiles for all sessions combined for (d) perception of the robot as a confidante and (e) robot anxiety measurement. $*p<0.05$ corrected.