Pairwise Reviews Ranking and Classification for Medicine E-Commerce Application

Abstract

E-Commerce applications provide an added advantage to customer to buy product with added suggestions in the form of reviews. Obviously, reviews are useful and impactful for customers those are going to a buy product. But these enormous amount of reviews create problem also for customers as they are not able to segregate useful ones. Therefore, there is a need for an approach which will showcase only relevant reviews to the customers. This same problem has been attempted in this research paper as this is a less explored area. Pairwise Review relevance ranking method is proposed in this research paper. This approach will sort reviews based on their relevance with the product and avoid showing irrelevant reviews. This work has been done in three phases- feature extraction, pairwise review ranking, and classification. The outcome is sorted list of reviews, review ranking accuracy and classification accuracy. Four classifiers- SVM, Random forest, Neural network, and logistic regression have been applied to validate ranking accuracy. Out of all four applied classification models, Random forest gives the best result. our proposed system is able to achieve 99.76% classification accuracy and 99.56% ranking accuracy for a complete dataset using random forest.