FNAARCNN: Fake News Detection Using an Attention    Augmented Residual Convolutional  Neural Network

Description

    FNAARCNN is a deep learning–based model developed for accurate fake news detection using textual content. The architecture integrates Residual Convolutional Neural Networks (ResCNN) with an attention mechanism to effectively extract hierarchical semantic features from news articles.

    Residual connections enable deeper feature learning by mitigating gradient degradation, while the attention mechanism highlights informative words and contextual patterns that contribute to misinformation detection.

    The model enhances robustness against noisy and diverse news data, supporting automated and scalable fake news classification in digital media platforms.

Input

 • News Text – Full textual content of the news article

Output

 • Fake (0) – The news article contains misinformation

 • Real (1) – The news article is legitimate and fact-based

Tags

#FNAARCNN #FakeNewsDetection #AttentionCNN #ResidualCNN #TextClassification #DeepLearning #NLP #MisinformationDetection #BinaryClassification #AIinMedia

References

1. Wang, Y., Ma, F., Jin, Z., Yuan, Y., Xun, G., Jha, K., Su, L. and Gao, J., 2018. EANN: Event Adversarial Neural Networks for Multi-Modal Fake News Detection. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2018), pp. 849–857.

2. Shu, K., Sliva, A., Wang, S., Tang, J. and Liu, H., 2017. Fake News Detection on Social Media: A Data Mining Perspective. ACM SIGKDD Explorations Newsletter, 19(1), pp. 22–36.

3. Zhang, X., Zhao, J. and LeCun, Y., 2015. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems (NeurIPS 2015), pp. 649–657.