Combating Cyberbullied Images in the Real World: A Comparative Study of CNN Architectures

Image-based cyberbullying brings more complexity compared to text-based forms, presenting new challenges that tra-ditional methods struggle to address. Owing to the rapid advancement of deep learning, computer vision technology has become a powerful tool to address this issue. In recent years, Convolutional Neural Networks (CNNs) have gained prominence for image processing and recognition because of their excellent feature extraction abilities. Initially, this paper conducts a comprehensive review of the literature in the fields of computer vision and cyberbullying detection and provides an extensive comparison of the performance among different CNN architectures, including VGG, ResNet, and WRNs, on a dataset of cyberbullying images. It shows and discusses that the VGG architecture outperforms other architectures in terms of performance and computational efficiency.