1. Business Ideas
  2. Business Plans
  3. Startup Basics
  4. Startup Funding
  5. Franchising
  6. Success Stories
  7. Entrepreneurs
  1. Sales & Marketing
  2. Finances
  3. Your Team
  4. Technology
  5. Social Media
  6. Security
  1. Get the Job
  2. Get Ahead
  3. Office Life
  4. Work-Life Balance
  5. Home Office
  1. Leadership
  2. Women in Business
  3. Managing
  4. Strategy
  5. Personal Growth
  1. HR Solutions
  2. Financial Solutions
  3. Marketing Solutions
  4. Security Solutions
  5. Retail Solutions
  6. SMB Solutions
Product and service reviews are conducted independently by our editorial team, but we sometimes make money when you click on links. Learn more.

Is That Online Business Review Phony? New Software Knows

If some of the online reviews of certain businesses' goods and services seem to be too good to be true, you may be right. Many of them are fake reviews placed by companies trying to game the system, researchers say.

Review sites are becoming targets for '"opinion spam"—phony reviews created by sellers to hype their own products and dump on the competition.  The problem is that human beings are usually lousy at identifying deceptive reviews.

But researchers at Cornell University may have good news. They are developing computer software that's skilled at ferreting out bogus reviews. Their software was able to pick out 90 percent of deceptive reviews in a batch of 800 reviews of Chicago hotels.

In the process, the researchers uncovered some key features to help determine if a review was spam and even discovered evidence of a correlation between the linguistic structure of deceptive reviews and fiction writing.

"While this is the first study of its kind, and there's a lot more to be done, I think our approach will eventually help review sites identify and eliminate these fraudulent reviews," said Myle Ott, a Cornell doctoral candidate in computer science, who presented the work the annual meeting of the Association for Computational Linguistics on behalf of his fellow Cornell researchers.

Ott cautioned that the work so far is only valid for hotel reviews, and for that matter, only reviews of hotels in Chicago. The next step, he said, is to see if the techniques can be extended to other categories, starting perhaps with restaurants and eventually moving to consumer products. He also wants to study negative reviews.

"Ultimately, cutting down on deception helps everyone," Ott said. "Customers need to be able to trust the reviews they read, and sellers need feedback on how best to improve their services."

Review sites might use this kind of software as a "first-round filter ," Ott suggested. If one particular hotel gets a lot of reviews that score as deceptive, the site will know to investigate further.

Reach BusinessNewsDaily senior writer Ned Smith at nsmith@techmedianetwork.com. Follow him on Twitter @nedbsmith.



Ned Smith
Ned Smith

Ned was senior writer at Sweeney Vesty, an international consulting firm, and was Vice President of communications for iQuest Analytics. Before that, he has been a web editor and managed the Internet and intranet sites for Citizens Communications. He began his journalism career as a police reporter with the Roanoke (Va.) Times, and was managing editor of American Way magazine and senior editor of Us. He was a Captain in the U.S. Air Force and has a masters in journalism from the University of Arizona.