Uncovering the most robust predictors of problematic pornography use - A large-scale machine learning study across 16 countries

Aug 4, 2026

The paper investigates which variables most strongly predict problematic pornography use using a large-scale machine learning approach. Data are analyzed across 16 countries, enabling cross-national assessment of predictor robustness and generalizability. It emphasizes identifying stable, high-importance predictors rather than relying on single-site findings, supporting more reliable risk understanding. The study consolidates a large international consortium of contributors, reflecting broad collaboration and data coverage.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages51

Reading Time2 h 9 min

AccessFree to download

Study overview

Machine learning approach and scope

Cross-country analysis

Robust predictor identification

Consortium contributions

Uncovering the most robust predictors of problematic pornography use: A large-scale machine learning study across 16 countries Beáta Bőthe 1,2,3†, Marie-Pier Vaillancourt-Morel2,3, Sophie Bergeron 1,3, Zsombor Hermann4, Krisztián Ivaskevics5, Shane W. Kraus6, Joshua B. Grubbs7,8, Problematic Pornography Use Machine Learning Study Consortium9-47 Members of the Problematic Pornography Use Machine Learning Study Consortium: Andrew Allen9, Rafael Ballester-Arnal 10, James Binnie 11, Daphne van de Bongardt12,13, Nicholas C. Borgogna 14,15, Jorge Cardoso 16, Lijun Chen 17, Carlos Chiclana 18,19, Zsolt Demetrovics20,21, Jacinthe Dion3,22, Brian A. Droubay23, Yaniv Efrati24, David P. Fernandez25, Fernando Fernández-Aranda26,27,28, Christopher G. Floyd29, Johannes Fuss30, Ateret Gewirtz-Meydan31, Mark D. Griffiths25, Seyed Ghasem Seyed Hashemi32, David C. Hodgins33, Campbell Ince34, Md. Saiful Islam35,36, Susana Jiménez-Murcia26,27,28, Lee Kannis-Dymand37, Yasser Khazaal38,39, Mónika Koós20, Kamil Kopcik40, Ariel Kor41,42, Ewelina Kowalewska43,44, Nathan Leonhardt45, Shaul Lev-Ran41,46,47, Karol Lewczuk48, Gemma Mestre-Bach 19, Syed Noor49,50, Gábor Orosz51, Claudia Savard3,52,53, Michael P. Schaub54, Luke Sniewski55, Aleksandar Štulhofer56, Fred Volk57, Magdalena Wizła47 1Département de Psychologie, Université de Montréal, Montréal, Canada 2Département de Psychologie, Université du Québec à Trois-Rivières, Trois-Rivières, Canada 3Centre de recherche interdisciplinaire sur les problèmes conjugaux et les agressions sexuelles (CRIPCAS) 4Department of Criminal Psychology, Faculty of Law Enforcement, National University of Public Service, Hungary 5Doctoral School of Law Enforcement, Faculty of Law Enforcement, National University of Public Service, Hungary 6Department of Psychology, University of Nevada, Las Vegas, Las Vegas, NV, USA 7Center on Alcohol, Substance use, And Addictions, University of New Mexico 8Department of Psychology, University of New Mexico 9 School of Health, University of the Sunshine Coast, Queensland, Australia 10Departmento de Psicología Básica, Clínica y Psicobiología. Facultad de Ciencias de la Salud. Universitat Jaume I de Castelló, Spain 11Division of Psychology, School of Applied Sciences, London South Bank University, UK 12Department of Psychology, Education and Child Studies; Erasmus School of Social and Behavioural Sciences; Erasmus University Rotterdam, The Netherlands 13Erasmus Love Lab 14Department of Psychological Sciences, Texas Tech University, United States 15Department of Psychology, University of South Alabama, United States 16LabPSI-Laboratory of Psychology, Egas Moniz School of Health and Science, Portugal 17Department of Psychology, School of Humanities and Social Sciences, Fuzhou University, Fujian, China 18Consulta Dr. Carlos Chiclana, Madrid, Spain 19Universidad Internacional de La Rioja, La Rioja, Spain 20Institute of Psychology, ELTE Eötvös Loránd University, Budapest, Hungary 21Centre of Excellence in Responsible Gaming, University of Gibraltar, Gibraltar, Gibraltar 22Département des sciences de la santé, Université du Québec à Chicoutimi, Canada 23Department of Social Work, Utah State University, Logan, UT, USA 24Faculty of Education, Bar-Ilan University, Israel 25Psychology Department, Nottingham Trent University, Nottingham, UK 26Clinical Psychology Unit, Bellvitge University Hospital-IDIBELL, Barcelona, Spain 27CIBERobn, Barcelona, Spain 28School of Medicine and Health Sciences, University of Barcelona, Barcelona, Spain 29Department of Psychology, Bowling Green State University, Bowling Green, USA 30Institute of Forensic Psychiatry and Sex Research, Center for Translational Neuro-and Behavioral Sciences, University of Duisburg-Essen, Essen, Germany 31School of Social Work, Faculty of Social Welfare and Health Sciences, University of Haifa, Israel 32Department of Psychology, Azarbaijan Shahid Madani University, Tabriz, Iran 33Departme

FAQs

这项研究主要研究什么问题？

研究聚焦于识别“有问题的色情使用”的最稳健预测因素，并用大规模机器学习进行建模与评估。

研究如何保证结果的跨地区可靠性？

通过覆盖16个国家的数据进行分析，从而检验预测因素在不同国家之间的稳健性与可推广性。

研究采用的核心方法是什么？

文中使用大规模机器学习研究来挖掘并比较不同变量对有问题色情使用的预测效力。

Aug 4, 2026

Upload by Emma Wilson