E-Commerce Recommendation over Big Data Based on early reviewers for effective product marke ting Prediction Rates

Abstract

Online reviews is the important source of information for users before selecting a product or making a decision. Early reviews of a product tend to have a high impact on the subsequent product sales.In this paper we study the behavior characteristics early reviewers through their posted early reviews.At first we divided the product lifetime into three stages (Early, majority and laggards).A person who post a reviews in early stage is consider as early reviewers. The Early reviewers are the first one who respond to the product at the beginning stage. We quantitatively characterize early reviewers based on their rating behaviors. We use k-means with PageRank to predicting the early reviewers.