HYBRID DEEP LEARNING MODEL FOR CYBERBULLYING DETECTION ON SOCIAL MULTIMODEL DATA

Abstract

Cyberbullying is the use of Information and Communication Technology (ICT) by individuals‟ to humiliate, tease, embarrass, taunt, defame and disparage a target without any face-to-face contact. Social media is the “virtual playground” used by bullies with the upsurge of social networking sites such as Facebook, Instagram, YouTube, Twitter etc. It is critical to implement models and systems for automatic detection and resolution of bullying content available online as the ramifications can lead to a societal epidemic. This research proffers a novel hybrid model for cyberbullying detection in three different modalities of social data, namely, textual, visual and info-graphic (text embedded along with an image). The all-in-one architecture, CNN-BoVW-SVM, consists of a convolution neural network (CNN) for predicting the textual bullying content and a support vector machine (SVM) classifier trained using bag-of-visualwords (BoVW) for predicting the visual bullying content. The info-graphic content is discretized by separating text from the image using Google Lens of Google Photos App. The processing of textual and visual components is carried out using the hybrid architecture and a Boolean system with a logical OR operation is augmented to the architecture which validates and categorizes the output on the basis of text and image bullying truth value. The model achieves a prediction accuracy of 84% which is acquired after performing tuning of different hyper-parameters.