Cerebro

Abstract

The recent boom in e-commerce has created active electronic communities where consumers share their thoughts about the product and the company. These reviews play a very important part in building customer opinion about the said item. For a popular product or service, there might be thousands of reviews, making it difficult for the customer to make an informed decision about the product. In this paper, we present a way to surface only those reviews that contain information relevant to the user. To address this problem, we try to surface out the reviews that are outliers to the general cluster of reviews during a particular time period.We are leveraging anomaly detection algorithms to achieve this.