A HYBRID DEEP LEARNING APPROACH FOR CYBERBULLYING DETECTION IN TWITTER SOCIAL MEDIA PLATFORM

Abstract

Cyberbullying has emerged as a pervasive issue within social media platforms, posing significant risks to users' well-being. To address this growing concern and enhance platform safety, this paper proposes a novel hybrid deep learning model, termed DEA-RNN, designed specifically for detecting cyberbullying on Twitter. The DEA-RNN model integrates Elman-type Recurrent Neural Networks (RNN) with an optimized Dolphin Echolocation Algorithm (DEA) to fine-tune RNN parameters and expedite training. Through comprehensive evaluation using a dataset comprising 10,000 tweets, we compared DEA-RNN's performance with state-of-the-art algorithms such as Bi-directional Long Short Term Memory (Bi-LSTM), SVM, Multinomial Naive Bayes (MNB), and Random Forests (RF). Our experimental findings demonstrate the superiority of DEA-RNN across all scenarios, showcasing its effectiveness in cyberbullying detection on the Twitter platform. Particularly noteworthy is DEA-RNN's exceptional performance in scenario 3, achieving an average accuracy of 90.45%, precision of 89.52%, recall of 88.98%, F1-score of 89.25%, and specificity of 90.94%.