Emotion and memory model for a robotic tutor in a learning environment

Muneeb Imtiaz Ahmad, Omar Mubin, Suleman Shahid, Joanne Orlando

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

Abstract

![CDATA[In this paper, we present an emotion and memory model for a social robot. The model allowed the robot to create a memory account of a child’s emotional events over 4 individual sessions. The robot then adapted its behaviour based on the developed memory. We tested our model through using the NAO robot. The robot was programmed to teach vocabulary to children during the popular game 'Snakes and Ladders'. We conducted a between-subject study with 24 children at a primary school to check the validity of our model. We also evaluated the impact of robot’s positive, negative, and neutral emotional feedback of the NAO robot on children vocabulary learning. Three groups of children (8/group) interacted with the robot for four different times during three weeks. Our results showed that the condition where the robot displayed positive emotional responses had a significant effect on the child’s learning performance as compared to the two other conditions: negative feedback and neutral feedback. In addition, our model helped children in improving their vocabulary.]]
Original languageEnglish
Title of host publicationProceedings of the Seventh ISCA workshop on Speech and Language Technology in Education 2017, August 25-26, 2017, DjurÓ§, Stockholm, Sweden
PublisherKTH Royal Institute of Technology
Pages26-32
Number of pages7
Publication statusPublished - 2017
EventISCA Workshop on Speech and Language Technology in Education -
Duration: 25 Aug 2017 → …

Conference

ConferenceISCA Workshop on Speech and Language Technology in Education
Period25/08/17 → …

Keywords

  • human robot interaction
  • education
  • machine learning

Fingerprint

Dive into the research topics of 'Emotion and memory model for a robotic tutor in a learning environment'. Together they form a unique fingerprint.

Cite this