ESOA-Based 1D-CNN Classification for Amazon Textual Review Sentiment Analysis of Mobile Phones

A trend toward the use of digital platforms for product marketing and profit margin enhancement is evident in the contemporary corporate environment. As a result, using deep learning methods to evaluate consumer sentiment in tweets based on product reviews becomes essential. The study's proposal is to use a big dataset and a one-dimensional convolutional neural network (1D-CNN) for the classification process in order to extract lexical characteristics for sentiment analysis. In order to do this, analysis is done on customer review datasets of Amazon items with an emphasis on reviews pertaining to mobile phones. To improve the performance and accuracy of the classifier, data preprocessing is first done. A lexical method is then used to efficiently compress the text via feature extraction. For the purpose of correctly assessing review emotions, efficient classification is essential. So, classification is done using the 1D-CNN method. The Egret Swarm Optimization Algorithm is used to adjust the 1D-CNN model's hyperparameters (ESOA). After this procedure, the research evaluates the 1D-CNN method's performance in relation to other techniques currently in use. The research concludes that the suggested method performs well overall, achieving 98.77% accuracy, 97.37% precision, 97.42% sensitivity, and 97.21% F-measure, respectively. These performance measures outperform those of current algorithms created in earlier research. The sentiment analysis of mobile phone evaluations inside the Amazon e-commerce system shows improved accuracy and efficiency when using the suggested 1D-CNN neural network approach.