Identifying Biased Reviews: An Analysis on Amazon Electronic Products

Abstract

Online reviews play a significant role in our community contributing to the prediction of the marketing situation, making industries modifying their advertising policies. Many consumers choose online reviews for making the decision to buy a specific product. In recent years, product sellers provide some lucrative offers to write biased reviews which are usually very positive that increases the rating of the products significantly. So it is very important to detect biased reviews for online shopping to help the consumers in their decision making to buy proper products. In this work, a new method has been developed for detecting those biased reviews generated on some products at Amazon. At first online reviews of Amazon product like- Fire Tablet, Alkaline Batteries, etc. are collected. Then sentiment analysis is introduced for calculating the sentiment score of the text reviews with the help of natural language processing. Naïve-Bayes-Analyzer model and TextBlob library are used to calculate the sentiment scores. Finally, statistical measurements are used to detect biased reviews.