Yelp Reviews Say More Than You Realized

Yelp reviews can have a tremendous impact – for better or for worse – on a business. They can dictate whether or not a customer decides to visit. This is one of the reasons the site/app is...
Yelp Reviews Say More Than You Realized
Written by Chris Crum
  • Yelp reviews can have a tremendous impact – for better or for worse – on a business. They can dictate whether or not a customer decides to visit. This is one of the reasons the site/app is so controversial with businesses. There may actually be more to reviews than meets the eye, however.

    Do believe Yelp reviews have any significant impact on your business? Let us know in the comments.

    Yelp has been offering researchers access to its data in the form of the Yelp Dataset Challenge, which includes data from Phoenix, Las Vegas, Madison, Waterloo, and Edinburgh. It’s made up of data from 42,153 businesses, 320,002 business attributes, 31,617 check-in sets, 252,898 users, 955,999 edge social graph, 403,210 tips, and 1,125,458 reviews.

    With the challenge, Yelp has been calling on academics to break ground in research with its data. Explaining the challenge, Yelp says:

    How well can you guess a review’s rating from its text alone? Can you take all of the reviews of a business and predict when it will be the most busy, or when the business is open? Can you predict if a business is good for kids? Has Wi-Fi? Has Parking? What makes a review useful, funny, or cool? Can you figure out which business a user is likely to review next? How much of a business’s success is really just location, location, location? What businesses deserve their own subcategory (i.e., Szechuan or Hunan versus just “Chinese restaurants”), and can you learn this from the review text? What makes a tip useful? What are the differences between the cities in the dataset? There is a myriad of deep, machine learning questions to tackle with this rich dataset.

    Researchers from Yahoo took Yelp up on the challenge, utilizing 200,000 of the available reviews to look at social signals that can be gleaned from Yelp, which can provide a better understanding of consumers’ interactions with businesses on the popular review site. As they note, Yelp isn’t just about the actual reviews.

    In a blog post, Yahoo Labs researchers Saeideh Bakhshi, David A. Shamma, and Partha Kanuparthy write:

    People on Yelp also log in and express their opinions, not as reviews, but as votes on reviews. In effect, it’s a higher granularity than a Flickr “favorite” or a Facebook “like,” as Yelpers cast their votes with the distinct sentiments of cool, funny, and/or useful. These votes are three kinds of “likes”; they are a minimal social signal that many online sites use for communication and recommendation. The three options that Yelp offers lets one investigate the implied meanings carried by these sentiments more accurately than many other social networks. But there’s something more here. In aggregate, a random person on Yelp might carry a running total of votes they have cast, including 469 useful votes, 192 cool votes, and 260 funny votes. The same could hold true for a venue. We began to wonder if we could understand something more from these votes; are they indicative of particular emotions? Do the votes represent some fingerprint of a Yelper or of an establishment?

    They found that the way people vote on reviews (including the sentiment of the text) has a relationship with the tone of the text and the text’s rating, depending on vote type. They say there is deeper meaning in signals like “cool,” “useful,” and “funny,” than those labels suggest.

    “While many would be correct in associating the useful and funny votes as representing reviews with the most amount of information or humor they contain, these signals are actually a proxy for negativity in reviews,” the researchers say. “A cool vote is more ambiguous in its meaning, but clearly associates with more positive reviews. Understanding these votes, or signals, and how they affect ratings can better inform customers as they come across reviews and take them into account for their own purposes; ultimately, they could alter one’s perception of a business, for better or worse.”

    The main takeaways are as follows:

    • Reviews that were voted useful and/or funny tended to have lower user ratings and generally carry a negative tone.
    • Reviews deemed to be cool by users tend to have a positive tone and higher user ratings.
    • Reviews written by members who are active for longer periods of time tend to receive more votes. Readers tend to prefer long and objective reviews.

    You can read the full research paper here. There is also some follow-up research available here.

    Have you ever considered the impact of how non-reviewing Yelp users are contributing to your business’ reputation by their interactions with existing reviews? Does it make a significant difference in your opinion? Share your thoughts in the comments.

    Images via Yelp, Yahoo

    Get the WebProNews newsletter delivered to your inbox

    Get the free daily newsletter read by decision makers

    Subscribe
    Advertise with Us

    Ready to get started?

    Get our media kit