CNN-LSTM Based on Crow Search Optimization Algorithm for Product Review Classification

Product reviews means an everyone’s opinion or views towards particular products or services that delivered to a specific company. In modern global, reviews of online product play a vital part in the estimation process of product in a company and their customers. The extracted features are selected by using the Chi-Squared technique and for the classification of product review proposed a model by utilizing the combined deep learning techniques like Convolutional Neural Network (CNN) and Long- Short Term Memory (LSTM) and it optimized by Crow Search Algorithm (CSA). CNN is used for capturing the local information and LSTM neural network is used for the long-distance dependencies. By utilizing the benefits of CNN and LSTM and it is optimized by CSA for the effective classification of product review. The proposed model performance is estimated by using the performance metrics like Accuracy, Recall, Specificity, Sensitivity and F1-score are 98.35%, 93.20%, 97.57%, 94.82% and 95.78% respectively. The proposed model is compared with other existing model in terms of performance metrics which shows the better performance results.