Explainable Hybrid Transformer Model Based Fake News Detection System
TL;DR
This paper presents an extensive study of fake news detection, which involves manually curated linguistic features, classic machine learning techniques, DL, transfomer, and fusion multimodal, and examines the key multimodal benchmark, the Fakeddit dataset.
Abstract
This new era of digitalization comes with great issues of democratic values, breach of people’s trust and hindrances to principles of welfare: distorted facts in media. Unimodal text detection can detect misleading text. However, social media is increasingly used for mismatched information involving many modalities. Mismatched information which includes misleading text along with manipulated images will challenge unimodal text detection. This paper presents an extensive study of fake news detection, which involves manually curated linguistic features, classic machine learning techniques, DL, transfomer, and fusion multimodal. We examine the key multimodal benchmark, the Fakeddit dataset. We also look at text , image based detection systems and multimodal detection systems. Lastly, we analyze the new explainable AI techniques like SHAP and LIME that make the detection systems more clear and trustworthy. We highlight certain research spheres that currently do not feature in the pertinent literature. Examples of these are dual-modality explainability, systems for the field and better integration of explainability in multimodal architectures.