A Comprehensive Analysis of Cyberbullying Detection Using Various Machine Learning Approaches

This study investigates the growing concern of cyberbullying, which has become prevalent due to the emergence of Web 2.0 and social networking platforms. Cyberbullying, which involves using technology to insult and torment people, can have significant psychological effects, particularly among young people, leading to depression and low self-esteem. In this digital age, cyberbullying is a pervasive and escalating problem that requires robust detection mechanisms. We critically evaluate the effectiveness of these algorithms, taking into account parameters such as prediction and training time, recall, F1-score, accuracy, and precision. By analyzing the results, we aim to identify the optimal algorithm that balances efficient detection and accurate classification of cyberbullying instances. Our research addresses the shortcomings of existing methodologies by providing a nuanced understanding of the strengths and limitations of each approach, paving the way for improved cyberbullying detection strategies. By studying cyberbullying and evaluating machine learning methodologies, we contribute to the ongoing efforts to create safer online environments. By leveraging machine learning and natural language processing, our research aims to contribute to the creation of a safer digital environment, thereby protecting vulnerable groups unsuspecting of the harmful effects of cyberbullying.