Review: Review Spam Detection

March 5, 2008
Authors: Nitin Jindal and Bing Liu
Year: 2007
Published in: The International World Wide Web Conference Committee (IW3C2)
Importance: Very High


First of all Dr. Vidy Potdar wrote a great review on this paper on his blog. After I wrote my review I realized that. so here is my review:

It is now a common practice for e-commerce Web sites to enable their customers to write reviews of products that they have purchased. Such reviews provide valuable sources of information on these products. They are used by potential customers to find opinions of existing users before deciding to purchase a product. They are also used by product manufacturers to identify problems of their products and to find competitive intelligence information about their competitors. Unfortunately, this importance of reviews also gives good incentive for spam, which contains false positive or malicious negative opinions. In this paper, we make an attempt to study review spam and spam detection. To the best of our knowledge, there is still no reported study on this problem.

My Review

Authors discuss about new kind of spam in web which is called, “Review Spam”. They believe that this kind of spam are different from previous spam, so do the method detection.

There are 2 type of Review Spam:

  1. Duplicate Spam – review which are duplicated for different products
  2. Spam classification – other spams review spams which are not duplicated and mislead real users.

They use Shingle method to detect duplicate spams. but there is challenge for detecting other type. So authors based their classification on duplicate spams as positive training examples and learn their suggested machine learning model to detect type 2 spam characteristic.

As author indicated in their paper, it is hard to detect spam only from content of review. So we need other kind of information (meta-information) about a person who write review and all reviewers to better detect spams with more accuracy.

All and all, this kind of spam, Review Spam, need more robust and accurate method so need more investigations

Important terms

Useful Refrences

  • Jindal, N. & Liu, B. Review Analysis. Tech. Report, 2007.
  • Jindal, N., & Liu, B. Identifying comparative sentences in text documents. SIGIR’2006.
  • Li, K., & Zhong, Z. Fast statistical spam filter by approximate classifications. SIGMETRICS 2006, 2006.
  • Popescu, A-M., & Etzioni, O. Extracting Product Features and Opinions from Reviews. EMNLP’2005.
  • Jindal, N., & Liu, B. Identifying comparative sentences in text documents. SIGIR’2006.