Exponential Distribution model for Review Spam Detection

Main Article Content

Jyoti G. Biradar


Online reviews capture the testimonials of real people and help shape the decisions of other consumers. It has become very crucial for e-Commerce trades to empower their end customers to write reviews about the services that they have utilized. Such reviews provide vital sources of information on these products/stores. Review information is utilized by the future potential customers before deciding on purchase of new products or services. These opinions or reviews are also exploited by marketers to find out the drawbacks of their own products or services and alternatively to find the vital information related to their competitor’s products or services. This in turn allows identifying weaknesses or strengths of the products/stores. Unfortunately, this significant usefulness of opinions has also raised the problem for spam, which contains forged positive or spiteful negative opinions. These reviews are written due to the financial gains associated with positive reviews, with often paid spam reviewers writing fake reviews to unjustly promote or demote certain products or businesses. Identifying such opinion spam reviews have become a challenge in opinion mining. Hence, in this work a novel approach exponential distribution model is used to find review spamicity. This method significantly outperforms several baselines and other methods.

Keywords: Reviews, review spam, multiple criteria, exponential distribution model


Download data is not yet available.

Article Details