Abstract
Progression in technology and innovation increases internet users, who post their perspectives on social media platforms regarding any product or service. It brings forth significant terms, i.e.,”feedback of users,” termed as sentiments and plays a substantial role for commercial organizations to analyze and find polarity related to their respective services. In Sentiment Analysis, the feature extraction phase is a crucial one that affects the entire process's processing. In the case of high dimensional Real- Time data, it leads to a sparse feature matrix and gives rise to steady processing. In this exploration work, we have proposed an Improved Optimized Feature Sentiment Classifier for Big Data (IOFSCBD) System, which deals with advancing the classifiers by giving improved values in each sort of dataset. Results show better execution of the Improved Optimized Feature Sentiment Classifier for Big Data system System.
Keywords: Ant Colony Optimization (ACO), BAT, Big Data, Natural Language Processing (NLP), Particle Swarm Optimization (PSO), Support Vector Machine (SVM).