Predictors of compulsive cyberporn use: A machine learning analysis.

Area of Science:

• Psychology
• Internet Studies
• Addiction Research

Background:

• Compulsive cyberporn use (CCU) is a growing concern, yet research on its predictors remains limited.
• Previous studies often relied on convenience samples, limiting generalizability.
• A comprehensive understanding of factors contributing to CCU is needed for targeted interventions.

Purpose of the Study:

• To assess the prevalence of compulsive cyberporn consumption in a broad sample of cyberporn users.
• To identify the most significant predictors of compulsive cyberporn use (CCU) from a diverse range of variables.
• To enhance the understanding of problematic pornography use for improved treatment and prevention.

Main Methods:

• An online questionnaire was administered to 1584 adult English speakers who had used cyberporn in the last six months.
• Data collected included sociodemographic, sexual, psychological, and psychosocial variables.
• Statistical analyses, including correlation, ANOVA, and machine learning, were employed to identify CCU predictors.

Main Results:

• 21.96% of participants exhibited symptoms of compulsive cyberporn use (CCU).
• The strongest predictors of CCU scores were identified as: craving for pornography, using pornography to suppress negative emotions, frequency of use, acceptance of rape myths, and anxious attachment style.
• These five factors emerged as the most significant contributors to compulsive cyberporn use.

Conclusions:

• This study identified key psychological and behavioral predictors of compulsive cyberporn use (CCU) in a large, diverse sample.
• Findings provide a deeper insight into the multifaceted nature of problematic pornography use.
• The identified predictors can inform the development of more effective compulsive cyberporn treatment and prevention programs.