Sentiment Analysis Of E-Commerce Website Using Ensemble Feature Selection

In any case, the content is normally large throughout nature due to the convenience of products in big amount with their information, offering by vendors, crowned with buyers render comments in the form of measure. Valuation become reflections connected with user approval based on a new scale [1]. Frauds are generally an overbearing analysis because they are engineered to stop detection[2]. The performance has been analyzed with 5 classification algorithms of SVM ,RF, NB, Gradient Boosting Classifier and Ridge classifier. The overall performance with accuracy has been evaluated with each classifier and feature importance.