Publication

Abstract : This paper describes a system that uses NGINX as the server to improve performance, combining advanced natural language processing (NLP) models with distributed computing. Fast and precise sentiment classification is provided by the system, which specializes in real-time sentiment analysis of massive amounts of text data. Scalability and dependability are guaranteed by distributed computing, and system responsiveness and dependability are boosted by NGINX’s improved load balancing and traffic management. Different load balancing algorithms are used to distribute network traffic among multiple servers so that no single server is overloaded. These algorithms include Round Robin, Least Connections, IP Hashing, Geographic Load Balancing, and Consistent Hashing. The algorithms random forest (RF), support vector machine (SVM), and decision tree were tested; random forest yielded the best results in terms of accuracy. The flask-developed backend of the system manages requests effectively and interfaces with NLP models. To sum up, this work presents a real-time, scalable sentiment analysis system that leverages NGINX, distributed computing, and sophisticated NLP models to achieve better performance. The system produces accurate sentiment classification and is very good at quickly analyzing large amounts of text data. This work provides a thorough framework for creating scalable and effective real-time sentiment analysis systems, setting the stage for further developments in the field. For applications like social media monitoring and customer feedback analysis, integrating cutting-edge NLP and ML algorithms into a distributed framework provides helpful advice on how to implement dependable and robust sentiment analysis.