Introduction The rapid growth of short video platforms has raised concerns about their impact on users’ mental health, particularly sleep quality. The aim of this research is to investigate the relationship between short video addiction and sleep quality among college students, examine the differential impacts of algorithm types (personalized vs. community-based) and content types on sleep parameters, and evaluate the effectiveness of a multi-component intervention. Methods Sixty college students (aged 18–25) meeting criteria for short video addiction (PSQI ≥5, daily usage ≥2 h) were randomly assigned to personalized algorithm ( n = 30) or community-based algorithm ( n = 30) groups. Sleep quality was measured using the Pittsburgh Sleep Quality Index (PSQI), actigraphy, and the Short Video Addiction Scale (SVA-S). The intervention combined cognitive behavioral therapy (CBT), digital technology tools (time-window control, brightness adjustment), and a social support system (“Sleep Guardian”). Results Personalized algorithms significantly worsened sleep quality compared to community-based algorithms (PSQI: 10.4 ± 2.3 vs. 8.7 ± 2.1, p = 0.003, Cohen’s d = 0.77). Entertainment content had the most detrimental effects on sleep parameters compared to knowledge and information content ( p 0.001, η 2 = 0.23). The multi-component intervention significantly improved sleep quality in both groups, with PSQI scores decreasing by 3.6 points in the personalized algorithm group and 2.8 points in the community-based group ( p 0.001, Cohen’s d = 1.71 and 1.46, respectively). Daily short video usage decreased by 47.1% and 54.3%, respectively. Conclusion Short video addiction significantly impacts sleep quality. The combination of personalized algorithms and entertainment content creates particularly detrimental conditions for sleep. A comprehensive intervention incorporating CBT, digital tools, and social support effectively improves sleep quality and reduces addiction symptoms.
Feng et al. (Tue,) studied this question.