Sentiment Analysis on Marketplace Review using Hybrid Lexicon and SVM Method

Abstract

Nowadays, especially during the Covid-19 pandemic time, there is an enormous rise in online transactions. There exist some marketplaces that provide review facilities to help customers in choosing the right products or sellers. Sentiment analysis is a study to classify a review text to sentiment classes Tables. In this paper, we present a study of sentiment analysis on marketplace review text using a hybrid method developed based on lexicon from Sentiwordnet 3.0 and Support Vector Machine (SVM) method. The experimental results show that the hybrid method outperforms the lexicon approach and SVM approach.