Download PDFOpen PDF in browserEnhancing Cyberbullying Detection Systems with Hybrid Machine Learning ModelsEasyChair Preprint 1373513 pages•Date: July 1, 2024AbstractCyberbullying has emerged as a pervasive issue in the digital age, posing significant challenges to the safety and well-being of individuals, especially among youth. Traditional detection systems often fall short in accurately identifying and mitigating such harmful behavior due to the complex, context-dependent nature of online interactions. This paper explores the enhancement of cyberbullying detection systems through the implementation of hybrid machine learning models, which leverage the strengths of various algorithms to improve detection accuracy and efficiency. By combining supervised learning techniques, such as Support Vector Machines (SVM) and Random Forests, with advanced neural network architectures, including Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), the proposed hybrid models can capture both linguistic nuances and contextual patterns in textual data. The study involves the collection and preprocessing of a comprehensive dataset from multiple social media platforms, followed by the training and evaluation of the hybrid models. Results demonstrate that hybrid models significantly outperform traditional single-algorithm approaches, achieving higher precision, recall, and F1 scores. The findings underscore the potential of hybrid machine learning models in creating more robust and effective cyberbullying detection systems, ultimately contributing to safer online environments. Future research directions include the integration of real-time detection capabilities and the application of these models across diverse languages and cultural contexts. Keyphrases: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Support Vector Machines (SVM)
|