• Volume: 1
• Issue:03
• Date: 01-03-2024

Title : Machine Learning Classifiers For Cyberbullying Detection- A Review

Abstract: Cyberbullying has become a pervasive issue in the digital age, affecting individuals across social media platforms, online forums, and communication networks. The complexity and scale of detecting cyberbullying in real-time make it a challenging task. Machine learning classifiers offer a promising approach for automating the detection process by identifying harmful and abusive content based on patterns in text, images, and user behavior. This review paper explores the state-of-the-art machine learning techniques applied to cyberbullying detection. We examine the performance of various classifiers such as Support Vector Machines (SVM), Random Forests, Naïve Bayes, Decision Trees, and deep learning models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The paper highlights key datasets, feature extraction methods (such as sentiment analysis, ngrams, and word embeddings), and evaluation metrics employed in the literature. Additionally, we discuss the strengths and limitations of each classifier in detecting nuanced forms of cyberbullying across different online platforms. The review concludes with insights into future research directions, focusing on improving model accuracy, handling multilingual data, addressing privacy concerns, and developing more robust and scalable systems for real-world deployment

Key Words: Cyberbullying Detection, Machine Learning, Support Vector Machine (SVM), Random Forest, Naïve Bayes, Deep Learning, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Text Classification, Sentiment Analysis, Online Safety, Social Media

Area: Engineering

• Approved ISSN: ----
• Paper Id: IJREISTU12
• Page No: 12-15

• Author: Nidhi koyale

---

• Co- Author: Dr. Pushparaj Singh Chauhan