Science Figures Out How To Identify Groups Of Fake Online Reviewers

Anyone who has sifted through anonymous “user” reviews of products is likely aware that there’s a good chance some of those comments were posted by shills trying to game the system to make the product look much better or worse than it is. While there are already a number of common-sense ways to suss out a bogus review, science has found a way to identify entire groups of review spammers.

A recent study by researchers at the University of Illinois at Chicago, with some help by Google, looked at ways of identifying the behavior of both individual review spammers and groups of spammers.

“Although labeling individual fake reviews and reviewers is very hard, to our surprise labeling fake reviewer groups is much easier,” write the researchers in their report titled Spotting Fake Reviewer Groups in Consumer Reviews.

Here is an example from the report:

Figures 1, 2, and 3 show the reviews of a group of three reviewers. The following suspicious patterns can be noted about this group: (i) the group members all reviewed the same three products giving all 5 star ratings; (ii) they posted reviews within a small time window of 4 days (two of them posted in the same day); (iii) each of them only reviewed the three products (when our Amazon review data was crawled); (iv) they were among the early reviewers for the products (to make a big impact). All these patterns occurring together strongly suggest suspicious activities. Notice also, none of the reviews themselves are similar to each other (i.e., not duplicates) or appear deceptive. If we only look at the three reviewers individually, they all appear genuine. In fact, 5 out of 9 reviews received 100% helpfulness votes by Amazon users indicating that the reviews are useful. Clearly, these three reviewers have taken total control of the sentiment on the set of reviewed products.

Check out a PDF of the entire report here.

Google-sponsored research identifies groups of bogus product reviewers [The Verge]