Big data-based artificial intelligence for efficient digital screen usage management among Chinese children and adolescents during the COVID-19 pandemic

Abstract

Abstract This study investigated screen-time behaviors of Chinese children and adolescents and the efficacy of artificial intelligence (AI)-based alerts in screen-time behavior correction. Data from 6,716 children and adolescents with AI-enhanced tablets that recorded behavioral and light environment data during use were analyzed. The mean daily screen time was 67.10 ± 48.26 min. The screen time of junior-high-school students exceeded 1.5 h (92.50 ± 75.06 min) and that of school-aged participants exceeded 4 h per week. Children younger than two years used tablets for more than 45 min per day. Learning accounted for more than 50% of participants’ screen time. The distance alarm was triggered 807,355 times. Some participants (31.03%, 2061/6643) used tablets for 1 h at an average distance < 50 cm. Over 70% of the participants used the tablet under an illuminance < 300 lx during the day and more than 60% under an illuminance < 100 lx at night. More than 85% of the participants’ ambient light exceeded 4,000 K color temperature at night. The screen time of school-aged participants was longer than that of preschool-aged children. The recorded illumination was insufficient and was paired with a high color temperature at night. AI can effectively remind children and adolescents to correct unhealthy behaviors during screen time.