Fake Reviews a Growing and Tenacious Problem in Social Media
April 20, 2012
Ah, sentiment and lies. Next Gen Market Research blogger Tom H. C. Anderson interviewed data mining expert Bing Liu in anticipation of his day-before workshop for the Sentiment Analysis Symposium in New York City early next month. He has titled his interview, “Practical Sentiment Analysis and Lies.” Interesting.
Professor Liu teaches at the University of Illinois at Chicago, in the Computer Science Department. His work on text analytics and detecting online ratings fraud was recently featured in the New York Times. Anderson posed Liu with questions on the upcoming workshop as well as on his work in general.
The words that caught my eye were in Liu’s response to the issue of detecting fake reviews:
“Social media is here to stay. Its content is also being used more and more in applications.
Something has to be done to ensure the integrity of this valuable source of information before it becomes full of fake opinions, lies and deceptive information. After all, there are strong motivations for businesses and individuals to post fake reviews for profit and fame. It is also easy and cheap to do so. Writing fake reviews has already become a very cheap way of marketing and product promotion.”
Important though the issue might be, Liu admits that ratting out fake reviews is a huge challenge. Almost impossible to identify simply by reading them, misleading missives must be discovered through secondary information, like aggregate reviewer behavior and the physical origins of a post. Apparently, a reliable method has yet to be developed.
So, let this be a reminder of something my Dad used to tell me: now, perhaps more than ever, you can’t believe everything you read.
Cynthia Murrell, April 20, 2012
Sponsored by Pandia.com
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
