This study examines how different robot dialogue systems (rule-based vs. large language model-based) and content types (emotional support vs. safety education) affect pediatric patients' responses during hospital-based robot-mediated interventions. Approximately 60 pediatric patients aged 2-9 years will be randomly assigned to interact with a social robot (LIKU) using either rule-based or LLM-based dialogue. Each child will participate in two activity sessions (emotional content and safety content) in randomized order. Primary outcomes include child engagement, emotional responses, robot perception, and activity preferences, assessed through standardized questionnaires (UEQ, Godspeed), child interviews, and behavioral observations. Additionally, 5 experts will evaluate content appropriateness and safety. This pilot study aims to provide foundational data for developing personalized pediatric robot programs in hospital settings, optimizing both dialogue approaches and content design based on individual child characteristics.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
SUPPORTIVE_CARE
Masking
SINGLE
Enrollment
60
10-15 minute structured activity focusing on emotional recognition, expression, and regulation through storytelling, discussion, and artistic activities (drawing, physical expression) with the LIKU social robot
10-15 minute structured activity focusing on safety awareness and emergency response behaviors through educational videos, discussions, and hands-on activities (crafts, physical practice) with the LIKU social robot
Samsung Medical Center
Seoul, South Korea
Child Engagement Level
Behavioral observation checklist assessing attention to robot, participation in activities, and task involvement. Scored by trained observers using standardized coding scheme based on video recordings.
Time frame: Immediately following each intervention session (assessed within 1 hour post-session)
User Experience
User Experience Questionnaire (UEQ) - standardized 7-point semantic differential scale measuring six dimensions: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty of robot interaction.
Time frame: Immediately following each intervention session (approximately 5 minutes post-session)
Robot Perception
Godspeed Questionnaire Series - standardized scale measuring five dimensions of robot perception: anthropomorphism, animacy, likeability, perceived intelligence, and perceived safety.
Time frame: Immediately following each intervention session (approximately 5 minutes post-session)
Content Appropriateness
Expert evaluation using 5-point Likert scale assessing developmental appropriateness, educational fit, robot speech pacing, content clarity, and activity flow. Evaluated by 5 pediatric development experts through video review.
Time frame: Within 2 weeks of session completion via video review
Activity Preference
Child interview using picture cards to identify preferred activities and content types (emotional support vs safety education). Children select and explain their preferences.
Time frame: Immediately following completion of both intervention sessions (approximately 5 minutes)
Content Comprehension
Child interview assessing understanding of activity content, key messages, and learning points from each session using age-appropriate questions.
Time frame: Immediately following each intervention session (approximately 3 minutes)
Robot Relationship Quality
Child interview and behavioral observation assessing perceived intimacy with robot, emotional attachment, social bonding, and willingness to interact with robot again.
Time frame: Immediately following intervention sessions (approximately 5 minutes)
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.