Writing fake online reviews? New Google algorithm will catch you out

Writing fake online reviews? New Google algorithm will catch you out

Summary: Changing online sentiment is hard enough. But fraudulently working together to try and control the sentiment about a product or web site is just plain wrong.

TOPICS: Google, Security

Consumers' purchase decisions are influenced by user generated online reviews.  The potential for posting fictitious reviews that sound authentic is causing concern. Deceptive opinion spam is a growing problem for the online review site communities.

Changing online sentiment is hard enough. But fraudulently working together to try and control the sentiment about a product is just plain wrong.

A new software algorithm was announced last week at the World Wide Web 2012 conference in Lyon, France.  It tries to detect groups of spammers working together to influence products.

Opinion spamming is quite common. Have a look at any successful web sites with multiple reviews on the site. Some reviewers try to game the system by promoting or demoting target products. Groups of reviewers can work collaboratively to write fake reviews and can often take total control of the sentiment of the site.

These fake reviewers or spammer groups are hard to detect using review content features or methods to detect abnormal behaviours or patterns. One reviewer could log on with multiple IDs, or there could be multiple reviewers that are paid to write reviews.

Timing is important when spotting spammers. Often spammers post similar reviews within a short time of each other (The Group Time Window) and use very similar language (Group Content Similarity).

But it is hard to detect fraudulent reviews. Have a look at these reviews of the Chicago Hilton Hotel and try to guess which is fraudulent:

1. "My husband and I stayed in the Hilton Chicago and had a very nice stay! The rooms were large and comfortable. The view of Lake Michigan from our room was gorgeous. Room service was really good and quick, eating in the room looking at that view, awesome! The pool was really nice but we didnt get a chance to use it. Great location for all of the downtown Chicago attractions such as theaters and museums. Very friendly staff and knowledgable, you cant go wrong staying here."

2. "We loved the hotel. When I see other posts about it being shabby I can't for the life of me figure out what they are talking about. Rooms were large with TWO bathrooms, lobby was fabulous, pool was large with two hot tubs and huge gym, staff was courteous. For us, the location was great across the street from Grant Park with a great view of Buckingham Fountain and close to all the museums and theatres. I'm sure others would rather be north of the river closer to the Magnificent Mile but we enjoyed the quieter and more scenic location. Got it for $105 on Hotwire. What a bargain for such a nice hotel."

The answer can be found on page 202 of the Online Review Communities document. It is hard to detect between fake and authentic reviews isn't it? It is almost impossible to recognise the spam by simply reading every review. More information is needed to make a good judgement. Arjun Mukherjee and Bing Liu from the University of Illinois at Chicago collaborated with Natalie Glance from Google which gave a Google Faculty Award to partially support the research.

Spotting Fake Reviewer Groups in Consumer Reviews focuses on the algorithm, GSRank which can consider relationships amongst groups, individual reviewers and products reviewed.

The software algorithm can detect review threads that are trying to get control of sentiment and label the 'spamicity' of the group in order that the group can be ranked and dealt with accordingly.

GSRank significantly outperformed the other algorithms in use, showing that spam reviewers can and will be caught.

Until then, careful moderation of posts to stop bursts of sentiment spamming might be our only option...

Related content:

Topics: Google, Security

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • They Both Seemed Suspicious

    Both those reviews seemed suspicious. The only clue that the second one might be real was that it alluded to possible negatives about the hotel (others had called it shabby; some might prefer to be closer to the Magnificent Mile), and fake reviews don't usually do that. It's possible that one might for camouflage, but usually it seems like the sponsors of the reviews don't seem to want any hint of negativity even though that's really a dead giveaway, which is why the first one seemed completely fake.
  • hard to tell, but

    in the first one "... you cant go wrong staying here.???
    looks like a sale pitch.
    The Linux Geek
  • How funny

    I find it quite ironic, that Google's new sentiment tool, will be used to stop SJVN bad mouthing everyone to make Google look better.
  • Fake Review

    Page 202 of the cited document, where we're supposed to find out which of the two is fake (agree it's #1), refers to a footnote. The footnote references a report on another web site, which upon examination is "under construction."

    So I guess we'll be left hanging.

    • This Article Was Great

      I thought this article was great! It was clean and well written. I certainly will continue to read this blog and encourage my friends to do the same.
      Your pal,
      The Marketing Heretic
    • It is #1

      When I checked page 202 of the document, the footnote read as follows:

      3 The first review is deceptive opinion spam.
  • Difference between the two

    The real one includes specifics such as details about the pool and room. You didn't have to so much as glance at the hotel website for the first one.
  • False reviews

    There are people who make a hobby of trashing restaurants that their reviews clearly show they have never actually been to. There are also those that do the opposite. There is no rationale behind this but to be disagreeable. The ones that bother me the most are the ones that go to a restaurant and because they had a problem finding a place to park, or had to wait 30 minutes for a table, don't like anything about the restaurant. Worse, they think they are justified.
  • Amazon reviews

    This same algorithm needs to be applied to Amazon app reviews. There are so many fake reviews there giving either 1 star for apps deserving 5 or vice versa. Many of them are obviously fake / spam reviews.
    • yes, fully agree with you.

      Use 5 star to promote, and 1 star to attack:

  • is it too hard to say...?

    is it too hard to say "we know who is spamming because we are tracking his/her IP" ?

    For example, i am using CloudFlare for my webiste and it detect some IP that are tagged as spammers.
    • Sometimes IP info isn't what you think it is...

      I have posted reviews and replies to different sites and wondered why some didn't show up (especially on Yelp). One site, I actually got a message from them saying it was rejected and I called them up and asked why... They said, it was because I was trying to 'spam' the site because they already had a review from someone with the same IP address so it kicked it back.

      Well, after talking to my network folks at work (where I did the review from as I am also writing this now), they told me that EVERYONE at my work (a College) - yes EVERYONE, shows as coming from the same IP address and we always will. Great... so because someone else from my work (we have over 1000 staff & faculty plus thousands of students who are on our network everyday) had already posted a review, nobody (out of thousands) could put up another review? That's just crazy...
      • That's dumb

        That site won't be around very long if they keep doing that. Not only do most workplaces use a single external IP address, really big ISPs like AOL and Earthlink randomly assign IP addresses from a pool to different users on a per-transaction basis. Thus one person will seem to come from many IP addresses over the course of a session, and different people will come in on the same IP address milliseconds apart.
        Robert Hahn
        • Who Cares

          Now Google is the reveiw police? I understand that consumers use reveiws to make informed buying decisions online but I'm peorsonally sick of google. They actually have time to police review sites, while trying to conquer the world, lol? Get a life.
  • My Wife and I really enjoyed this Article!

    Seriously, if you can't tell a real review from fake, you shouldn't be shopping on line. I personally try to find a video review. Much more difficult to fake and there is typically enough information there for you to make your on opnion regardless of what the person says.
  • Very easy problem to fix

    All companies have to do is set up a way to verify you bought an item before you can review it. Easy to do with online purchases through amazon, etc. But they would have to figure out a way to verify in store purchases. I see so many amazon reviews from people that bought the item at Bestbuy. Verify purchases, then allow review. Problem solved.
    Gam3r 4 Life
    • Not so easy...

      The only problem with this proposed solution is that a reviewer doesn't always have to purchase something to be qualified to write a review, probably only true for in store experiences. I have written a negative review for a restaurant that I never ended up buying anything from. Sat down with some friends, put in an order, got a couple drinks and waited an hour, no food ever arrived. We walked up to the desk to see what was going on because our waiter had apparently left, there was no record of us in the system. They told us the drinks were on the house and we could stay if we liked, they would rush our food but we had places to be. There is a scenario where no purchase was made but yet a review was still legitimate.

      Another scenario that this could happen is extremely poor customer service at a retail shop, so bad that people decide to leave before a purchase is ever completed. Although I see your point, I dont think confirming a purchase solves the problem.
  • Wow

    I never really knew it was a wide spread problem. I did guess that the first review was the fake one. Primarily because the second mentioned some things that people might find negative, and also mentioned where they purchased it and for how much.
  • seo services india

    I do agree with you. Already bookmarked your article. Thanks
    seo india
  • Can this be reported

    Does anyone know if you can actually report things like this to Google or does the algorithm have to find it.