Single Valued Neutrosophic Sets with Optimal Support Vector Machine for Sentiment Analysis

Abstract

Sentiment analysis (SA) is mainly employed to investigate the polarity of the sentiment existent in a content. It assist in understanding the opinions or feelings expressed by people. It find useful in several application areas such as e-commerce, education, etc. Natural language processing (NLP) and machine learning tools can be employed for SA. In this view, this study develops a Single Valued Neutrosophic Sets with Optimal Support Vector Machine (SVNS-OSVM) model for SA. The major intention of the SVNS-OSVM model is to identify the existence of sentiments exist in the data. The SVNS-OSVM model initially performs data pre-processing to transform the input data into a useful format. In addition, SVNS model is applied to derive word embeddings. Then, SVM model is applied for the detection and classification of sentiments. At the last level, the improved particle swarm optimization (IPSO) algorithm is used to fine tune the parameters involved in the SVM model. For ensuring the improved outcomes of the SVNS-OSVM model, a wide range of simulations were performed and the results are inspected under several aspects. The comparative study highlighted the betterment of the SVNS-OSVM model compared to recent approaches.