ADVANCING FAKE NEWS DETECTION: HYBRID DEEP LEARNING WITH FASTTEXT AND EXPLAINABLE AI

Abstract

The rapid expansion of social media and digital news platforms has accelerated the spread of fake news, posing serious threats to public opinion, trust, and societal stability. Addressing this issue requires accurate, efficient, and interpretable detection systems. This paper presents an advanced hybrid deep learning approach for fake news detection that integrates FastText embeddings with powerful neural network architectures. The proposed model combines the strengths of FastText in capturing semantic relationships and subword information with deep learning techniques such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for effective feature extraction and sequence modeling. Additionally, Explainable Artificial Intelligence (XAI) techniques are incorporated to enhance transparency by providing insights into the model’s decision-making process. Experimental evaluations demonstrate that the hybrid model significantly outperforms traditional machine learning approaches in terms of accuracy, precision, recall, and F1-score. The integration of explainability further improves user trust by identifying key features and words influencing predictions. Overall, this research contributes to the development of a robust, scalable, and interpretable fake news detection system suitable for real-world applications in combating misinformation.