Social media is an online platform with millions of users and is utilized to spread news, information, world events, discuss ideas, etc. During the COVID-19 pandemic, information and ideas are shared by users both officially and by citizens. Here, the detection of useful content from social media is a challenging task. Hence, natural language processing (NLP) and deep learning are widely utilized for the analysis of the emotions of people during the COVID-19 pandemic. Hence, this research introduces a deep learning mechanism for identifying the sentiment of the people by considering the online Twitter data regarding COVID-19. The intelligent lead-based BiLSTM is utilized to analyze people's sentiments. Here, the loss of the classifier while learning the data is eliminated through the incorporation of the intelligent lead optimization. Hence, the loss is reduced, and a more accurate analysis is obtained. The intelligent lead optimization is devised by considering the role of the informer in identifying the enemy base to safeguard the territory from attack along with the Monarch's knowledge. The performance of the intelligent lead-based BiLSTM for the sentiment analysis is assessed using the metrics like accuracy, sensitivity, and specificity and obtained the values of 96.11, 99.22, and 95.35%, respectively, which are 14.24, 10.45, and 26.57% enhanced performance compared to the baseline KNN technique.
The sentiment analysis relying on the aspect of online reviews is utilized for identifying the polarity of the given review. Nowadays, many methods are introduced for aspect-based sentiment analysis (ABSA) using neural networks, and many methods failed to consider contextual information exploitation to make the performance more accurate. Hence, this research proposed an optimized deep learning method for the detection of the aspect and to identify the polarity. Hence, in this research, an optimized deep learning technique for the ABSA is introduced by considering the online reviews, in which the deep learning classifiers are trained with the proposed Fabricius ringlet optimization (FRO) algorithm to reduce the loss that helps to enhance the accuracy of sentiment polarity prediction. The proposed FRO is developed by the hybridization of the behavioral nature of the Fabricius and the ringlet in feeding for the determination of the global best solution. The tuning of the weights and biases of the classifier enhance the performance of the classifier. The objective behind the tuning is to minimize the loss function while training and to enhance the accuracy of aspect extraction and polarity prediction of sentiment. Based on a study of the existing approach, the suggested FRO-based hybrid deep learning method is significantly improved; its accuracy, sensitivity, and specificity are 87.06%, 90.83%, and 79.37%, respectively, with a training percentage of 40%. The accuracy, sensitivity, and specificity of the existing technique have also been enhanced for aspect restaurant values, which are 87.53%, 96.06%, and 79.88% with a 60% training percentage. Similar to that, Twitter values for accuracy, sensitivity, and specificity are reported to be 89.08%, 99.35%, and 79.70%, respectively, with an 80% training percentage. The proposed method obtained the 90.13%, 99.35%, and 81.10% accuracy, sensitivity, and specificity from the assessment of the FRO-based hybrid deep learning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.