Fake News Detection Using Machine Learning with AttentionBased Multi-Scale Feature Fusion

Abstract

Fake News Detection Using Machine Learning presents a fundamental challenge in ML, NLP, Misinformation Detection. Existing approaches, including Naive Bayes, SVM, and RF, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing FakeDetect, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on LIAR, FakeNewsNet using stratified 10-fold cross-validation. Our method achieves a mean accuracy (%) of 94.7% on the primary benchmark, surpassing the nearest baseline by 2.9 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 38.5% reduction in computational cost relative to comparable hybrid architectures and convergence within 55 epochs on all benchmark datasets.