Detecting and Preventing Cyberbullying on Social Media Platforms Using Deep Learning Techniques

EasyChair Preprint 13729

Abstract

The pervasive growth of social media has brought significant advancements in communication and connectivity, yet it has also facilitated the rise of cyberbullying, a serious and widespread issue affecting users worldwide. This study explores the application of deep learning techniques to detect and prevent cyberbullying on social media platforms. By leveraging advanced algorithms and large datasets, deep learning models can effectively identify harmful content, patterns of abusive behavior, and potential victims and perpetrators. The research delves into various architectures, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to analyze text, images, and videos for signs of bullying. Additionally, the study addresses the integration of these models into real-time monitoring systems, providing proactive interventions and alerts to mitigate the impact of cyberbullying. Ethical considerations, data privacy, and the importance of user education and awareness are also discussed. This research aims to contribute to a safer online environment, fostering positive interactions and protecting users from the detrimental effects of cyberbullying through the innovative application of deep learning technologies.

Keyphrases: Convolutional Neural Networks (CNNs), Deep learning technologies., Recurrent Neural Networks (RNNs)

@booklet{EasyChair:13729,
  author    = {Abey Litty and Zakarya Jahin and Zakarya Jesan},
  title     = {Detecting and Preventing Cyberbullying on Social Media Platforms Using Deep Learning Techniques},
  howpublished = {EasyChair Preprint 13729},
  year      = {EasyChair, 2024}}