Effectiveness of Machine Learning Methods in Detecting Grooming: A Systematic Meta-Analytic Review

Abstract

This study presents a systematic review (SR) and meta-analysis (MA) on the use of machine learning (ML) methods for detecting online grooming, a process of manipulation and sexual abuse towards children. An SR was conducted to identify and describe ML methods and effectiveness indicators for detecting grooming. From 26 studies obtained from IEEE, Web of Science, Scopus, Springer, and PubMed databases, 11 ML methods were meta-analyzed for each of the four reported indicators: accuracy (ACC), precision (P), recall (R), and F1 Score (F1). The most effective methods were Multilayer Perceptron (MLP) and Support Vector Machine (SVM), detecting an ACC=92% for MLP and R=72% for SVM, respectively. This study is pioneering in meta-analyzing ML methods applied to the effectiveness in detecting grooming. The results highlight the efficacy of certain algorithms and contribute to the identification of online predators. A crucial aspect of cybersecurity for preventing child sexual abuse.