Self-Attention Based Progressive Generative Adversarial Network optimized with Aquila Optimization Algorithm for Sentimental Analysis of Fake News Detection

Abstract

Fake news on social media is increased in recent years. This has led to the requirement for efficient algorithms for detecting fake news. This research proposes SAPGAN-AOA-FND, a novel framework combining a self-attention-based progressive generative adversarial network (SAPGAN) enhanced using the Aquila optimization algorithm (AOA) tailored specifically for fake news identification. The proposed methodology encompasses four key steps: data collection, data pre-processing, feature extraction, and detection. Initially, a fake news dataset is sourced from Kaggle fake news dataset, followed by a rigorous pre-processing phase involving tokenization, stop-word removal, filtering, lemmatization, hashtag removal, lowercasing, stemming, and multi-word grouping. Subsequently, a lexicon hybrid N-gram2vector model is employed for comprehensive feature extraction, encompassing content level, user level, social level, local, and global features. The extracted features are provided to the self-attention-based progressive generative adversarial network (SAPGAN) model, which typically lacks explicit optimization techniques for ensuring accurate fake news detection. To address this gap, the AOA is introduced to enhnce the weight parameters of the SAPGAN technique, enhancing its discriminative capabilities. Furthermore, the proposed approach conducts sentiment analysis to discern positive and negative sentiments within real along fake news. It observes a prevalence of positive sentiment in real news and a greater occurrence of negative sentiment in fake news. The efficiency of SAPGAN-AOA-FND is rigorously evaluated utilizing performance metrics including sensitivity, precision, recall, f-measure, specificity, accuracy, and computational complexity. The proposed technique offers 20.67%, 33.89% and 24.67% higher accuracy and 28.76%, 30.67% and 34.89% higher specificity comparing with existing techniques like Fake news detection using cross modal attention residual with multichannel convolutional neural networks (CARMN-FND), Fake news detection using capsule neural networks (CapNN-FND) and Convolutional neural network utilizing margin loss for fake news detection (CNN-FND), respectively.