AI system analyses student data to prevent chronic nonattendance

TOKYO - A Japanese city is exploring the use of artificial intelligence (AI) to address the challenging issue of school refusal, with student data analysed to predict who may soon stop attending due to anxiety, bullying, or other reasons, Kyodo News Agency reported.

The city education board of Toda in Saitama Prefecture, near Tokyo, trialled an AI system for the year ending March, hoping to provide teachers with a tool to identify and support struggling students.

The number of primary and junior high school students not attending school for 30 days or longer has consistently risen in Japan over the past decade, with the figure for fiscal 2022 reaching a record just shy of 300,000.

The Ministry of Education, Culture, Sports, Science, and Technology attributed this rise to a growing recognition that students do not necessarily need to attend school.

The AI-based prediction system assesses data on students, including attendance, academic achievement and health conditions. It also takes into account records of their visits to school nurses and bullying reports.

The system then makes predictions based on past data of students who stopped attending classes, showing how close a student is to the risk of chronic nonattendance. It colour-codes the probability figures for each student, ranging from the highest, "red," to "pink," "orange," and the lowest, "yellow."

During the trial run at 18 primary and junior high schools, the programme identified a total of 1,193 students as being at high risk. Based on the outcome, teachers determined that 265 of these students should receive priority assistance, taking into account their behaviour and other factors, according to the education board.

To address privacy concerns, the education board established rules to safeguard personal data and prevent the AI-generated predictions from being used in any discriminatory manner against students.

It also informed parents in advance that they could opt out of the project to block the use of their children's data. Only those in school management positions, such as principals, had access to the results.

By using objective data, it is possible that we can prevent students from rejecting school," said Makiko Nakamuro, a Keio University professor and expert in education economics.

"But we need to carefully consider the need to ensure privacy by clearly explaining the objective and extent of data usage," she added. - BERNAMA-KYODO