Memory-Based Personalization for Fostering a Long-Term Child-Robot Relationship
summary
A memory-based personalization system stores children’s answers and uses an artificial cognitive agent to query them, selecting from templated mini-dialogues written by professional writers and adapting content with N=46, 5 sessions over two months. Manipulations include explicit memory references, narrative-branch selection, and personalized greetings like unique handshakes. Results show willingness to continue stays stable with personalization while it drops in control (significant at session five), closeness scores rise with personalization by session five, no change in self-disclosure, and more positive social cues (more smiling).
AI-written summary · about
chapters (8)
- 0:00Intro
- 0:13Research Motivation
- 1:08Design Foundation
- 2:10Design Specification - Mini-dialogs
- 3:09Design Specification - Memory-based Personalization
- 5:42Longitudinal User Study
- 6:41Results
- 9:08Conclusions
related talks
16mSomeone to Read with: Design of and Experiences with an In-Home Learning Companion Robot for Reading
28mPreference Learning from Minimal Human Feedback for Interactive
01h 11mEmotional AI and Empathic Technologies: Rights, Children and Domestication.
06mInterview with Jong Lee
15mSensing and Handling Engagement Dynamics in Human-Robot Interaction Involving Peripheral ...
08mA Simple Nod of the Head: The Effect of Minimal Robot Movements on Children's Perception of a ...
21mTeaching Language to Deaf Infants with a Robot and a Virtual Human
22mWhy That Nao? How Humans Adapt to a Conversational Humanoid Robot in Taking Turns-at-Talk