Advancing Fake News Detection: Hybrid DeepLearning with FastText and Explainable AI

Abstract

The widespread propagation of misinformation on social media platforms poses a significantconcern, prompting substantial endeavors within the research community to develop robust detectionsolutions. Individuals often place unwavering trust in social networks, often without discerning the originsand authenticity of the information disseminated through these platforms. Hence, the identification of media-rich fake news necessitates an approach that adeptly leverages multimedia elements and effectively enhancesdetection accuracy. The ever-changing nature of cyberspace highlights the need for measures that mayeffectively resist the spread of media-rich fake news while protecting the integrity of information systems.This study introduces a robust approach for fake news detection, utilizing three publicly available datasets:WELFake, FakeNewsNet, and FakeNewsPrediction. We integrated FastText word embeddings with variousMachine Learning and Deep Learning methods, further refining these algorithms with regularization andhyperparameter optimization to mitigate overfitting and promote model generalization. Notably, a hybridmodel combining Convolutional Neural Networks and Long Short-Term Memory, enriched with FastTextembeddings, surpassed other techniques in classification performance across all datasets, registering accu-racy and F1-scores of 0.99, 0.97, and 0.99, respectively. Additionally, we utilized state-of-the-art transformer-based models such as BERT, XLNet, and RoBERTa, enhancing them through hyperparameter adjustments.These transformer models, surpassing traditional RNN-based frameworks, excel in managing syntacticnuances, thus aiding in semantic interpretation. In the concluding phase, explainable AI modeling wasemployed using Local Interpretable Model-Agnostic Explanations, and Latent Dirichlet Allocation to gaindeeper insights into the model’s decision-making process.

Tasks

Reproductions