School Attendance Prediction among Students with Autism: A Deep Learning-based Framework

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that affects the areas of social communication and behavior. The term “spectrum” refers to the wide range of symptoms observed across individuals with ASD. Many children with ASD experience difficulty with daily functioning at school andhome. ASD prevalenceincreases in the United States, with the most recent prevalence of 1.9%. Given the wide range of social and learning, difficulties experienced by children with ASD, it is paramount that they are able to attend school to receive the appropriate range of interventions. School absenteeism (SA) is a significant concern given its association with many negativeconsequences such as school drop-out.Early prediction of SA would help school districtto implement effective interventions to ameliorate this issue. Due to its heterogeneity, students with ASD show within-group differences concerning their SA. This research introduces a deep learning-based framework for predicting short-and long-term SA of students with ASD. The Long Short-Term Memory (LSTM) algorithm is used to predict short-term SA. Similarly, Multilayer Perceptron(MLP) and Random Forest (RF) algorithms are used to predict long-term SA. The proposed framework achieves a high accuracy of 89% and 90% to predict short-term and long-term SA, respectively.