An Efficient CNN-based LSTM Approach to Detect the Rumor Prediction in COVID-19 Data using Fuzzy based Deep learning

Abstract

Abstract As the traditional rumor detection method is concerned, reduce in the data accuracy may influence the observation directivity and lack in the extraction of feature datasets. In order to overcome the above problem, here the modified rumor prediction model is proposed using deep learning with the integration of CNN in order to improve the data accuracy with the help of neural networks. First, the continuous bag of words (CBOW) model is modified to define the window context based on the definition of the weighted module. Then, CNN gets modified with the association of the attention module added along with the output of the weighted module as it helps to identify the feature incompleteness in the long sequence of online social networks. The attention module along with CNN with the function of max pooling and upsampling layer in order to extract the features in the text effectively. Then, the extracted feature is given into the softmax layer for performing text classification to identify and predict the rumor in the online social network. Based on the online samples, the analysis is conducted on the proposed model based on certain parameter such as, data accuracy, precision, recall and F1-Score as it shows better performance as compared to the other existing models like LSTM based Fuzzy deep learning, deep recurrent Q-learning and adaptive deep transfer learning.