CNN, RNN-LSTM Based Hybrid Approach to Detect State-of-the-Art Stance-Based Fake News on Social Media

Abstract

Fake news is a new phenomenon related to false information and fraud that spreads through online social media or traditional news media. Today, fake news can be easily created and distributed across many social media platforms and has a widespread impact on the real world. It is critical to develop efficient algorithms and tools for early detection of how false information is disseminated on social media platforms and why it is successful in deceiving users. Most research methods today are based on machine learning, deep learning, feature engineering, graph mining, image and video analysis and newly developed datasets and web services for detecting deceptive content. Therefore, a strong need emerges to find a suitable method that can easily detect false information. A hybrid approach has suggested using the CNN model and RNN-LSTM model to detect false information from this study. First, NLTK toolkit has used to remove stop words, punctuations and special characters from the text. Then the same toolkit applies to tokenize the text and preprocesses the text. From there on, GloVe word embeddings have added to the preprocessed text. Higher-level features of the input text extract from the CNN model using convolutional layers and max-pooling layers. Long-term dependencies between word sequences capture from RNN-LSTM model. The suggested model also applies dropout technology with Dense layers to enhance the efficiency of the hybrid model. Results of the suggested hybrid model have shown that the suggested CNN, RNN-LSTM based Hybrid approach achieves the highest accuracy of 92% by surpassing most of the classical models today with Adam optimizer and Binary Cross-Entropy loss function.