Friendy: A Deep Learning based Framework for Assisting in Young Autistic Children Psychotherapy Interventions
Abstract
The management of children with autism is a complex and challenging task due to the symptoms related to the disorder that affect their cognitive and behavioral functioning. This makes it difficult for them to process information and adapt to new situations, leading to non-cooperative tendencies during therapy sessions, which can slow down their progress. To support professionals and enhance the therapy experience for these children, a deep learning and contextual chatbot technology based framework, named ”Friendy,” has been proposed and implemented. The results of its performance testing show a high accuracy rate of 80.5% and the experimentation with independent professionals demonstrate its promising potential for scalability and integration into future therapy processes. The framework provides a valuable solution to the difficulties encountered in the management of children with autism, offering an innovative and effective approach to their care.
Keywords
Human-Machine Interaction, system design, Autism care, Computer Aided Psychotherapy, Affective Computing
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
S. Hadri and A. Bouramoul, "Friendy: A Deep Learning based Framework for Assisting in Young Autistic Children Psychotherapy Interventions," in Journal of Communications Software and Systems, vol. 19, no. 1, pp. 30-38, February 2023, doi: 10.24138/jcomss-2022-0074
@article{hadri2023friendydeep,
author = {Sid Ahmed Hadri and Abdelkrim Bouramoul},
title = {Friendy: A Deep Learning based Framework for Assisting in Young Autistic Children Psychotherapy Interventions},
journal = {Journal of Communications Software and Systems},
month = {2},
year = {2023},
volume = {19},
number = {1},
pages = {30--38},
doi = {10.24138/jcomss-2022-0074},
url = {https://doi.org/10.24138/jcomss-2022-0074}
}