Exploring the Risk Factors of Cyberbullying Among Chinese Adolescents: The Important Role of Cybervictimization

The goal of the present study was to identify predictive factors related to cyberbullying by using supervised machine learning in a sample of Chinese adolescents during the COVID-19 pandemic. Participants included 2053 (M_age=16.36 years, SD = 1.14 years; 44.6% boys) adolescents from Fujian province, China. Data on cyberbullying, cybervictimization, socializing online, problematic smartphone use, parental trust and alienation, and media habits were collected from self-reports surveys. Several machine learning algorithms were used to train the statistical model for gender. The psychological variables for modeling cyberbullying were trained using many simulated replications on a random subset of participants, and externally tested on the remaining subset of participants. Shrinkage algorithms (lasso, ridge, and elastic net regression) performed slightly better than other algorithms. Results from the training subset generalized to the test subset, without substantial worsening of fit using traditional fit indices. The results indicated that cybervictimization demonstrated the largest relative contribution in predicting cyberbullying, followed by gender, parent alienation, and problem internet use. Implications and suggestions on the importance of cybervictimization when studying cyberbullying are discussed.