Chronic absences from school can hamper a student’s education, but children with autism are particularly susceptible to falling behind when they don’t receive the specialized instruction and resources they need.
What if there was a way to find a pattern of absences and flag school administrators when it becomes a major concern?
The research of two Binghamton University faculty members was recently published in Natureit’s Journal of Scientific Reports explores this idea using student absenteeism data from the University institute for child development (CIM) to identify individual patterns of absenteeism for each student.
Founded by Distinguished Service Professor Raymond Romanczyk in 1974, IAS helps local youth with intellectual disabilities. For this study, Professor Jennifer Gillis Mattson from the Department of Psychology at Harpur College of Arts and Sciences teamed up with Assistant Professor Daehan Won from the Department of Systems Science and Industrial Engineering at Thomas J. Watson College of Engineering to analyze these absentee counts using intelligence and deep learning.
Absenteeism among the general student population can lead to poor academic performance, relationship difficulties, increased high-risk behaviors, school dropout, and inability to find viable employment. Students with developmental disabilities, ADHD (attention deficit/hyperactivity disorder), and autism account for some of the highest rates of chronic absenteeism, but many of the reasons for these high rates are not well understood , according to Gillis Mattson, who is the ICD. Associate Director. The absence of class time can disrupt their academic progress and their access to a range of services available at school, such as occupational therapy.
Won tried several AI algorithms used in systems science to search for long-term patterns that could predict when future absences would occur. It didn’t exactly go as planned.
“We did an initial analysis and found that it was impossible to create a simple pattern of attendance, especially with autistic students, because each student had a different pattern for missing school,” Won said. “Even parents cannot predict their children. However, we have a large data set, so we decided to use artificial intelligence to develop an individualized attendance model for each student while capturing hidden or complex patterns.
The retuned goal is for AI and deep learning to help school administrators identify when student absences reach a critical level specifically defined for that student. Ideally, this process would be proactive and identify the risk of chronic absenteeism before it occurs so that the school and family can partner to improve child attendance.
“When kids are away, when do we start to think it’s a real problem or a trend?” said Gillis Mattson. “Humans are not really good at detecting them. Many factors are likely contributing to this, delaying our opportunities to respond and support families long before concerns about attendance reach current thresholds for action.
To expand their research in the future, Gillis Mattson and Won will approach other schools to request their truancy records and see if their data analysis matches what they see at the ICD for validation. They would also like to collect more information directly from families, such as reasons for absences and other potential factors, as well as better demographic profiles. This data collection could lead to the development of a smartphone or tablet app so parents can more easily report the information, in addition to policy changes regarding how best schools identify and support families.
Gillis Mattson and Won also need a school year where students are learning regularly in classrooms, not remotely from home due to the COVID-19 pandemic.
“Everything that we talk about absenteeism gets really complicated with COVID, because of quarantine, exposure, isolation, etc.,” Gillis Mattson said. “It’s hard to think about attendance in this context other than, ‘Oh my God, the kids are missing a lot of school during COVID!’ This is a huge problem for all children for many reasons, I hope we are at a positive turning point and that school attendance will be less affected in the future.
Won admits he was unfamiliar with ICD work before beginning his transdisciplinary research with Gillis Mattson, but he appreciated the opportunity to expand his knowledge.
“I learned a lot about how to approach problems, and it was a really good opportunity for me to increase my research skills and consider a new area,” he said. “I’ve said the same to my students, who have worked on industrial issues, that we now know the logistics of special education and why it’s a problem.”