Artificial Intelligence-Based Mobile Application for Emotion Sensing for Children Through Art

Stud Health Technol Inform. 2022 Jun 6:290:1130-1131. doi: 10.3233/SHTI220302.

Abstract

In this paper, we develop an artificial intelligence (A.I.) based Emotion Sensing Recognition App (ESRA) to help parents and teachers understand the emotions of children by analyzing their drawings. Four different experiments were conducted using a combination of two datasets. The deep learning model was trained using the Fastai library in Python. The model classifies the drawings into positive or negative emotions. The model accuracy ranged from 55% to 79% in the four experiments.

MeSH terms

  • Artificial Intelligence*
  • Child
  • Emotions
  • Humans
  • Mobile Applications*
  • Parents
  • Physical Therapy Modalities