Paper Key : IRJ************189
Author: Vadde Hema,Yadavally Sreevidya,Sangam Akaash,Ch. Rajesh
Date Published: 03 Mar 2024
Abstract
Online reviews have become an important source of instruction for users before manufacture an informed procure decision. Early reviews of a product tend to have a high effect on the ensuing product sales. In this paper, we take the initiative to study the behavior characteristics of early reviewers through their posted reviews on two real-world large ecommerce platforms, i.e., Amazon. A user who has posted a review in the early stage is contemplating as an untimely observer. We quantitatively characterize early reviewers based on their rating behaviors, the helpfulness scores received from others and the correlation of their reviews with product popularity. Our method has a number of advantages over current ones. Firstly, it considers the review language in its whole instead of just the rating or score. This enables us to record the subtleties of the review content that conventional review analytics could miss. Secondly, it integrates an extensive range of text preparation methods to guarantee that the numerical vector representation of the review text is accurate. Thirdly, it makes use of a machine learning algorithm that can identify intricate patterns in the data and forecast outcomes with accuracy.