Predictors of compulsive cyberporn use: A machine learning analysis

Abstract

Introduction: Compulsive cyberporn use (CCU) has previously been reported among people who use cyberporn. However, most of the previous studies included convenience samples of students or samples of the general adult population. Research examining the factors that predict or are associated with CCU are still scarce.In this study, we aimed to (a) assess compulsive cyberporn consumption in a broad sample of people who had used cyberporn and (b) determine, among a diverse range of predictor variables, which are most important in CCU scores, as assessed with the eight-item Compulsive Internet Use Scale adapted for cyberporn. Materials and Methods: Overall, 1584 adult English speakers (age: 18–75 years, M = 33.18; sex: 63.1 % male, 35.2 % female, 1.7 % nonbinary) who used cyberporn during the last 6 months responded to an online questionnaire that assessed sociodemographic, sexual, psychological, and psychosocial variables. Their responses were subjected to correlation analysis, analysis of variance, and machine learning analysis. Results: Among the participants, 21.96% (in the higher quartile) presented CCU symptoms in accordance with their CCU scores. The five most important predictors of CCU scores were related to the users’ strength of craving for pornography experiences, suppression of negative emotions porn use motive, frequency of cyberporn use over the past year, acceptance of rape myths, and anxious attachment style. Conclusions: From a large and diverse pool of variables, we determined the most important predictors of CCU scores. The findings contribute to a better understanding of problematic pornography use and could enrich compulsive cyberporn treatment and prevention.

Keywords

• Addiction
• Cyberporn
• Compulsive cyberporn use
• Machine learning