EXPLORING NEURAL NETWORK TOPOLOGIES FOR THE DETECTION OF FAKE NEWS: A HYBRID OF CONVOLUTIONAL AND RECURRENT NEURAL NETWORK

Researchers in the field of artificial intelligence are increasingly interested in exploring how to spot and counteract the spread of fake news.When compared to machine learning approaches, deep learning methods are superior in terms of their ability to reliably identify instances of false news.This study analyses the efficacy of various neural network topologies in the classification of news items into two distinct categories: false and real.This work takes into account three separate models: a core Recurrent Neural Network (RNN), a Convolutional Neural Network (CNN), and a hybrid model that merges both CNN and RNN layers.The RNN with four layers is the most complex model.When determining each model's overall performance, criteria such as accuracy, precision, and recall rates are taken into consideration.According to the findings, Recurrent Neural Networks (RNNs) show an amazing skill in capturing sequential dependencies, which results in an astounding accuracy rate of 99.16%.The degree of precision sees a big boost when it's applied with the help of a Recurrent Neural Network (RNN) that has four layers.Due to the fact that it is able to pick up on minute regional specifics, CNN is able to attain an impressive accuracy rate of 99.05% in addition to an excellent recall.By properly managing the trade-off between precision and recall, the hybrid model is able to efficiently attain a high degree of accuracy, particularly 98.84% of the target accuracy.The aforementioned results highlight the adaptability of various neural network designs in the context of distinguishing between real and false news, hence revealing key insights that have the potential to be implemented in practical scenarios involving the verification of information and the evaluation of its validity.